Search

Precision agriculture tools like decision support systems increasingly use machine‐learning algorithms and other types of artificial intelligence (AI) to analyze large quantities of agricultural data and provide recommendations to producers and crop advisers. However, several barriers threaten adoption of these tools. Three papers in the recent Agronomy Journal special section, "Machine Learning in Agriculture," explore this phenomenon and offer solutions and opportunities for building trust in these technologies. [ABSTRACT FROM AUTHOR]

In the contemporary data-driven era, the fields of machine learning, deep learning, big data, statistics, and data science are essential for forecasting outcomes and getting insights from data. This paper looks at how machine learning approaches can be used to anticipate solar power generation, assess heat exchanger heat transfer efficiency, and predict the thermo-physical properties of nanofluids. The review specifically focuses on the potential use of machine learning in solar thermal applications, perovskites, and photovoltaic power forecasting. Predictions of nanofluid characteristics and device performance may be more accurately made with the development of machine learning algorithms. The use of machine learning in the creation of new perovskites and the assessment of their effectiveness and stability is also included in the review. Additionally, the paper explores developments in artificial intelligence, particularly deep learning, in this area and offers insights into techniques for forecasting solar power, including PV production, cloud motion, and weather classification. [ABSTRACT FROM AUTHOR]

Multimodal emotion recognition, that is, emotion recognition uses machine learning to generate multi-modal features on the basis of videos which has become a research hotspot in the field of artificial intelligence. Traditional multi-modal emotion recognition method only simply connects multiple modalities, and the interactive utilization rate of modal information is low, and it cannot reflect the real emotion under the conflict of modal features well. This article first proves that effective weighting can improve the discrimination between modalities. Therefore, this paper takes into account the importance differences between multiple modalities, and assigns weights to them through the importance attention network. At the same time, considering that there is a certain complementary relationship between the modalities, this paper constructs an attention network with complementary modalities. Finally, the reconstructed features are fused to obtain a multi-modal feature with good interaction. The method proposed in this paper is compared with traditional methods in public datasets. The test results show that our method is accurate in It performs well in both the rate and confusion matrix metrics. [ABSTRACT FROM AUTHOR]

• Many ML algorithms are used to identify the main determinants of a bank default. • We use of a graph neural network that has never been used in a financial context. • We obtain a balanced dataset by customizing the heuristic oversampling method. • Like previous literature, we show that neural network outperforms other approaches. • We include, for the first time, competition among the possible default determinants. The financial sector is very interested in Artificial Intelligence due to the opportunities that it offers, especially those related to methods of machine-learning. The aim of this paper is to employ a variety of machine-learning algorithms to identify the main determinants of bank default and to understand the impact of each variable on it. Bank default is one of the most studied topics in financial literature because of the severity of its consequences on the whole economic system. However, little attention has been paid to the identification of the major determinants of bank failures via machine-learning approaches. This paper employs several machine-learning algorithms, including a graph neural network that has never been used in a financial context. Another novelty is the implementation of a balanced dataset by customising the heuristic oversampling method based on k-means and synthetic minority over-sampling technique. This paper also deals with the inclusion of competition among the possible default determinants. The dataset consists of all the banks in the Euro Area in the period 2018–2020. The results obtained are useful from both micro- and macro-economic points of view. [ABSTRACT FROM AUTHOR]

This paper introduces the Ulimisana Optimisation Algorithm enabled Population Based Training (PBT-UOA) framework which allows for hyperparameters to be fine-tuned using a population based meta-heuristic algorithm at the same time as parameters are being optimised. Models are trained until near-convergence on the updated hyperparameters and the parameters of the best performing model are shared to warm start the other models in the next hyperparameter tuning iteration. In the PBT-UOA, all models are trained using the same dataset. This framework performed better than the Bayesian Optimisation algorithm. This paper also introduces the Ulimisana Optimisation Algorithm enabled Federated Learning (FL-UOA) framework which is an extension of the PBT-UOA. This framework is introduced to address the challenges of scattered datasets and privacy that is presented by the increase in connected end-devices. The FL-UOA learns on local data in scattered end-devices without sending datasets to a central server. The training datasets in local end-devices are used to evaluate models trained in other end-devices. The performance metrics are used to update the Social Trust Network (STN) of the FL-UOA framework. The FL-UOA outperformed the classic Federated Learning framework. This STN updating technique was tested in Machine Learning (ML) Unfairness to see how well it functioned as a regularisation term. This was achieved by training different models on subsets that contained datasets representing only specific sensitive groups. Results showed that by updating the hyperparameters while learning the parameters on the dataset scattered across different devices, the FL-UOA, takes advantage of diversified learning and reduces the ML Unfairness for models trained on group specific datasets. [ABSTRACT FROM AUTHOR]

How to derive an investor's preference is vital for investment advisors and online lending platforms for targeted marketing strategies, e.g., market segmentation and financial product recommendation. However, investor preference analysis usually depends on judgments from human investment experts, which are inherently subjective and costly. Intelligent investment advisors (or Robo-advisors), supported by cutting-edge technologies such as machine learning and artificial intelligence, are established to relieve these pending issues. This paper employs an online optimization framework to obtain investors' preferences for further financial product recommendations. This proposed method allows us to update the investor's preference for newly-arriving data sets and tackle the situation where plenty of missing values in investors' records are present. Unlike the black-box-like machine learning approach, our method can provide more managerial implications regarding why one financial product/service is preferred. Real-world data set from an online financial platform is used to compare the existing approaches and shows the stronger and more stable performance of our method when facing different data-missing types and situations with different missing degrees, followed by a recommendation system application. [ABSTRACT FROM AUTHOR]

As a sub-branch of Artificial Intelligence (AI), Machine Learning (ML) is an inductive method of problem solving which can accomplish tasks that once required human participation and discretion. As governments and other institutions increasingly deploy ML-based systems to predict, rate and act upon individuals' behaviour or personal traits, there is growing political and legal demand for transparency so that the outcome of these systems could be interpretable, and thus contestable where necessary. Previous research has revealed that transparency in automated decisionmaking (ADM) entails not only openness and disclosure in the conventional sense but further administrative and technical measures such as the algorithmic audit or black-box testing of these systems. The implementation of such broadened scope of transparency inevitably involves the reproduction and/or adaptation of the relevant informational elements and components of the ML-based systems. This gives rise to the questions: (1) to what extent reliance on Intellectual Property (IP) rights could excuse automated decision-makers from the obligation of making transparent and contestable decisions, e.g., under Article 22 of the General Data Protection Regulation (GDPR); (2) what are the counter-arguments based on statutory exceptions and limitations restricting IP rights; and (3) what may be the possible solutions either within the IP regime or through regulatory intervention. Overall, the paper aims obtain a macro-view of the potential areas of conflict between the possible transparency measures/tools and the relevant IP regimes - i.e., copyright, sui generis database right and trade secret protection. [ABSTRACT FROM AUTHOR]

Explainable artificial intelligence (XAI) is gradually becoming a key component of many artificial intelligence systems. However, such pursuit of transparency may bring potential privacy threats to the model confidentially, as the adversary may obtain more critical information about the model. In this paper, we systematically study how model decision explanations impact model extraction attacks, which aim at stealing the functionalities of a black-box model. Based on the threat models we formulated, an XAI-aware model extraction attack (XaMEA), a novel attack framework that exploits spatial knowledge from decision explanations is proposed. XaMEA is designed to be model-agnostic: it achieves considerable extraction fidelity on arbitrary machine learning (ML) models. Moreover, we proved that this attack is inexorable, even if the target model does not proactively provide model explanations. Various empirical results have also verified the effectiveness of XaMEA and disclosed privacy leakages caused by decision explanations. We hope this work would highlight the need for techniques that better trade off the transparency and privacy of ML models. • We propose XaMEA, three XAI-aware model extraction attack architectures. • We further carry out XAI-aware model extraction attacks against non-explanation target models. • We evaluate the attack effectiveness of XaMEA with an exhaustive set of experiments. [ABSTRACT FROM AUTHOR]

This paper presents a method called Interval Incremental Learning (IIL) to capture spatial and temporal patterns in uncertain data streams. The patterns are represented by information granules and a granular rule base with the purpose of developing explainable human-centered computational models of virtual and physical systems. Fundamentally, interval data are either included into wider and more meaningful information granules recursively, or used for structural adaptation of the rule base. An Uncertainty-Weighted Recursive-Least-Squares (UW-RLS) method is proposed to update affine local functions associated with the rules. Online recursive procedures that build interval-based models from scratch and guarantee balanced information granularity are described. The procedures assure stable and understandable rule-based modeling. In general, the model can play the role of a predictor, a controller, or a classifier, with online sample-per-sample structural adaptation and parameter estimation done concurrently. The IIL method is aligned with issues and needs of the Internet of Things, Big Data processing, and eXplainable Artificial Intelligence. An application example concerning real-time land-vehicle localization and tracking in an uncertain environment illustrates the usefulness of the method. We also provide the Driving Through Manhattan interval dataset to foster future investigation. [ABSTRACT FROM AUTHOR]

• Explainable framework for meta-learning. • Efficiency and high causality. • Intervention and counterfactual. With the growing convergence of artificial intelligence and daily life scenarios, the application scenarios for intelligent decision methods are becoming increasingly complex. The development of various machine learning algorithms has benefited all disciplines of study, but choosing which algorithm is most suitable for a certain problem among a large number of algorithms is a challenge that every field must overcome. Another challenge at the practical application level is that machine learning algorithms currently trained with large amounts of data are primarily black-box and uninterpretable. This indicates that these methods pose potential risks and are difficult to rely on, thus hindering their application in sensitive fields such as finance and healthcare. The first challenge can be overcome by using meta-learning to combine data and prior knowledge to efficiently and automatically select the machine learning models. The second challenge remains to be addressed due to the lack of interpretability of traditional meta-learning techniques and deficiencies in transparency and fairness. Achieving the interpretability of meta-learning in autonomous algorithm selection for classification is crucial to balance the need for high accuracy and transparency of machine learning models in practical application scenarios. This paper proposes EFFECT , an interpretable meta-learning framework that can explain the recommendation results of meta-learning algorithm selection and provide a more complete and accurate explanation of the recommendation algorithm's performance on specific datasets combined with business scenarios. Extensive experiments have demonstrated the validity and correctness of this framework. [ABSTRACT FROM AUTHOR]

• Explainable framework for meta-learning. • Efficiency and high causality. • Intervention and counterfactual. With the growing convergence of artificial intelligence and daily life scenarios, the application scenarios for intelligent decision methods are becoming increasingly complex. The development of various machine learning algorithms has benefited all disciplines of study, but choosing which algorithm is most suitable for a certain problem among a large number of algorithms is a challenge that every field must overcome. Another challenge at the practical application level is that machine learning algorithms currently trained with large amounts of data are primarily black-box and uninterpretable. This indicates that these methods pose potential risks and are difficult to rely on, thus hindering their application in sensitive fields such as finance and healthcare. The first challenge can be overcome by using meta-learning to combine data and prior knowledge to efficiently and automatically select the machine learning models. The second challenge remains to be addressed due to the lack of interpretability of traditional meta-learning techniques and deficiencies in transparency and fairness. Achieving the interpretability of meta-learning in autonomous algorithm selection for classification is crucial to balance the need for high accuracy and transparency of machine learning models in practical application scenarios. This paper proposes EFFECT , an interpretable meta-learning framework that can explain the recommendation results of meta-learning algorithm selection and provide a more complete and accurate explanation of the recommendation algorithm's performance on specific datasets combined with business scenarios. Extensive experiments have demonstrated the validity and correctness of this framework. [ABSTRACT FROM AUTHOR]

This paper designs and simulates a circular heatsink (HSK) with a novel geometry. A number of cylindrical pin-fins (PIFs) are placed on the HSK. The flow of alumina/water nanofluid (NF) enters from the middle of the HSK, passes through the PIFs, goes toward the outer curvature, and exits from the HSK. Constant thermal flux is applied at the bottom of the HSK. The variables include the length of PIFs changing from 5 to 20 mm, the distance between PIFs varying from 10 to 15 mm, and the diameter of PIFs changing from 1 to 4 mm. The effect of these variables on the maximum of the HSK, the average temperature (T-AV) of the HSK is examined. Finally, numerical optimization is done on the results using machine learning and artificial intelligence in terms of the minimum HSK temperature. The flow of NF is simulated using a two-phase model and the finite element method (FEM). An increment in the length of the PIFs from 5 to 20 reduces the T-AV by 11.42 K. An increment in the diameter of the PIFs from 1 to 4 reduces the T-AV of the HSK by 5.98 K. [ABSTRACT FROM AUTHOR]

Investigating the entropy production (ETP) and inertial number can help to improve the efficiency of heat transfer devices, for this reason, in this paper, the study of the ETP of nanofluid (NNF) flow in a two-dimensional cavity was studied. The NNF flow is affected by the horizontal magnetic field (MGD). Also, the Bejan number (Be) of the flow was also studied for different states of the mentioned parameters. The cavity had two hot and cold walls and two insulated walls, the cold wall above which was also movable. On the lower warm wall, there are 3 blades in the shape of a triangle, the height of each of which was changed individually from 0.1 to 0.7 and its effect on entropy changes and Be was investigated. Finally, using artificial intelligence, the best conditions for having the lowest Be and ETP for the range of variables were checked. The NNF was simulated in two phases and the simulation was done in FORTRAN software using SIMPLE algorithm. The results of this study showed that the largest amount of Be was present in the longest length of the triangular obstacles, but the lowest value of the Be was in the low values of the height of theobstacles and did not necessarily occur in the lowest values of the heights. The highest amount of entropy was produced at the lowest height of the left obstacle and the highest height of the middle obstacle. Also, the amount of ETP at higher altitudes on the right side of the obstacle was greater than its lower altitudes. [ABSTRACT FROM AUTHOR]

• Explanation Sets, a new framework that unifies counterfactuals and semifactuals. • Counterfactuals and semifactuals are defined in terms of a similarity measure. • Restrictions and preferences over the explanations are defined using a neighborhood. • A taxonomy for set-based representations. Explainable Machine Learning (ML) is an emerging field of Artificial Intelligence that has gained popularity in the last decade. It focuses on explaining ML models and their predictions, enabling people to understand the rationale behind them. Counterfactuals and semifactuals are two instances of Explainable ML techniques that explain model predictions using other observations. These techniques are based on the comparison between the observation to be explained and another one. In counterfactuals, their prediction is different, and in semifactuals, it is the same. Both techniques have been studied in the Social Sciences and Explainable ML communities, and they have different use cases and properties. In this paper, the Explanation Set framework, an approach that unifies counterfactuals and semifactuals, is introduced. Explanation Sets are example-based explanations defined in a neighborhood where most observations satisfy a grouping measure. The neighborhood allows defining and combining restrictions. The grouping measure determines if the explanations are counterfactuals (dissimilarity) or semifactuals (similarity). Besides providing a unified framework, the major strength of the proposal is to extend these explanations to other tasks such as regression by using an appropriate grouping measure. The proposal is validated in a regression and classification task using several neighborhoods and grouping measures. [ABSTRACT FROM AUTHOR]

Measuring risk is at the center of modern financial risk management. As the world economy is becoming more complex and standard modelling assumptions are violated, the advanced artificial intelligence solutions may provide the right tools to analyse the global market. In this paper, we provide a novel approach for measuring market risk called Encoded Value-at-Risk (Encoded VaR), which is based on a type of artificial neural network, called Variational Auto-encoders (VAEs). Encoded VaR is a generative model which can be used to reproduce market scenarios from a range of historical cross-sectional stock returns, while increasing the signal-to-noise ratio present in the financial data, and learning the dependency structure of the market without any assumptions about the joint distribution of stock returns. We compare Encoded VaR out-of-sample results with twelve other methods and show that it is competitive to many other well-known VaR algorithms presented in the literature. [ABSTRACT FROM AUTHOR]

Purpose: To be more effective, artificial intelligence (AI) requires a broad overall view of the design and transformation of enterprise architecture and capabilities. Maturity models (MMs) are the recognized tools to identify strengths and weaknesses of certain domains of an organization. They consist of multiple, archetypal levels of maturity of a certain domain and can be used for organizational assessment and development. In the case of AI, quite a few numbers of MMs have been proposed. Generally, the links between AI technology, AI usage and organizational performance stay unclear. To address these gaps, this paper aims to introduce the complete details of the AI maturity model (AIMM) for AI-driven platform companies. The associated AI-Driven Platform Enterprise Maturity framework proposed here can help to achieve most of the AI-driven platform companies' objectives. Design/methodology/approach: Qualitative research is performed in two stages. In the first stage, a review of the existing literature is performed to identify the types, barriers, drivers, challenges and opportunities of MMs in AI, Advanced Analytics and Big Data domains. In the second stage, a research framework is proposed to align company value chain with AI technologies and levels of the platform enterprise maturity. Findings: The paper proposes a new five level AI-Driven Platform Enterprise Maturity framework by constructing a formal organizational value chain taxonomy model that explains a vast group of MM phenomena related with the AI-Driven Platform Enterprises. In addition, this study proposes a clear and precise description and structuring of the information in the multidimensional Platform, AI, Advanced Analytics and Big Data domains. The AI-Driven Platform Enterprise Maturity framework assists in identification, creation, assessment and disclosure research of AI-driven platform business organizations. Research limitations/implications: This research is focused on the basic dimensions of AI value chain. The full reference model of AI consists of much more concepts. In the last few years, AI has achieved a notable drive that, if connected appropriately, may deliver the best of expectations over many application sectors across the field. For this to occur shortly in machine learning, especially in deep neural networks, the entire community stands in front of the barrier of explainability. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is widely acknowledged as a crucial feature for the practical deployment of AI models in industry. Our prospects lead toward the concept of a methodology for the large-scale implementation of AI methods in platform organizations with fairness, model explainability and accountability at its core. Practical implications: AI-driven platform enterprise maturity framework can be used for better communicate to clients the value of AI capabilities through the lens of changing human-machine interactions and in the context of legal, ethical and societal norms. Social implications: The authors discuss AI in the enterprise platform stack including talent platform, human capital management and recruiting. Originality/value: The AI value chain and AI-Driven Platform Enterprise Maturity framework are original and represent an effective tools for assessing AI-driven platform enterprises. [ABSTRACT FROM AUTHOR]

In response to fighting COVID-19 pandemic, researchers in machine learning and artificial intelligence have constructed some medical knowledge graphs (KG) based on existing COVID-19 datasets, however, these KGs contain a considerable amount of semantic relations which are incomplete or missing. In this paper, we focus on the task of knowledge graph embedding (KGE), which serves an important solution to infer the missing relations. In the past, there have been a collection of knowledge graph embedding models with different scoring functions to learn entity and relation embeddings published. However, these models share the same problems of rarely taking important features of KG like attribute features, other than relation triples, into account, while dealing with the heterogeneous, complex and incomplete COVID-19 medical data. To address the above issue, we propose a graph feature collection network (GFCNet) for COVID-19 KGE task, which considers both neighbor and attribute features in KGs. The extensive experiments conducted on the COVID-19 drug KG dataset show promising results and prove the effectiveness and efficiency of our proposed model. In addition, we also explain the future directions of deepening the study on COVID-19 KGE task. [ABSTRACT FROM AUTHOR]

The rapid integration of intelligent processes and methods into information systems in the Artificial Intelligence (AI) era has led to a substantial shift towards autonomous software decision-making. This evolution necessitates robust human oversight, especially in critical domains like Healthcare, Education, and Energy. Human trust in AI plays a vital role in influencing decision-making processes of users interacting with AI. This paper presents VIRTSI (V ariability and I mpact of R eciprocal T rust S tates towards I ntelligent systems), a novel rigorous computational model for human-AI Interaction. VIRTSI simulates human trust states, spanning from overtrust to distrust, through user modelling. It comprises: 1. A trust dynamics representational model based on Deterministic Finite State Automata (DFAs), illustrating transitions among cognitive trust states in response to AI-generated replies. 2. A trust evaluation model based on Confusion Matrices, originating from machine learning and Accuracy Metrics, providing a quantitative framework for analysing human trust dynamics. As a result, this is the first time that trust dynamics have been thoroughly traced in a representational model and a method has been developed to assess the impact of possibly harmful states like overtrust and distrust. An empirical study on the recently launched Large Language Model of generative AI, ChatGPT (version 3.5), provides a radical underexplored AI-generated platform for evaluating the human-AI interaction through VIRTSI. The study involved 1200 interactions of real users as well as AI experts together with experts in two very different domains of evaluation, namely software engineering and poetry. This study traces trust dynamics and the emerging human-AI interaction, in concrete examples of real user synergies with generative AI. The research reveals the vital role of maintaining normal trust states for optimal human-AI interaction and that both AI and human users need further steps towards this goal. The real-world implications of this research can guide the creation and evaluation of user interfaces with AI and the incorporation of functionalities in the development of generative AI chatbots in terms of trust by providing a new rigorous DFA representational method of trust dynamics and a corresponding new perspective of confusion matrix evaluation method of the dynamics' impact in the efficiency of human-AI dialogues. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to advancing artificial intelligence (AI) through the development of the Complex Recurrent Spectral Network (ℂ -RSN), an innovative variant of the Recurrent Spectral Network (RSN) model. The ℂ -RSN model introduces localized non-linearity, complex fixed eigenvalues, and a distinct separation of memory and input processing functionalities. These features enable the ℂ -RSN to evolve towards a dynamic, oscillating final state that bear some degree of similarity with biological cognition. The model's ability to classify data through a time-dependent function, and the localization of information processing, is demonstrated by using the MNIST dataset. Remarkably, distinct items supplied as a sequential input yield patterns in time which bear the indirect imprint of the insertion order (and of the separation in time between contiguous insertions). • The C-RSN overcomes some limitations in existing neural network models. • C-RSN introduces localized non-linearity, complex eigenvalues and a separated memory. • The network evolves towards a dynamic, oscillating final state. • The model's efficacy is demonstrated through empirical evaluation. • C-RSN is able to process sequential inputs keeping track of the insertion order. [ABSTRACT FROM AUTHOR]

The use of artificial intelligence for decision support and automation has shown tremendous potential in many areas. The ability to explain the decisions made by a machine learning algorithm is fundamental to facilitating the widespread use of this type of tool. There are many important real-world problems where the cost of the decisions depends on the characteristics of each example: these are called example-dependent cost (EDC) problems. For this type of classification problem, an appropriate formulation that takes into account the decision costs is fundamental both for the design of the classifier and for the explanation of its decisions. In this paper, we propose COCOA, an explanation method designed for EDC problems based on a Bayesian discriminant. The proposed method can provide counterfactual samples generated by considering decision costs. The COCOA method provides valid and plausible counterfactuals with a high success rate, which can be actionable, diverse, and sparse, achieving a remarkable improvement in terms of cost over five state-of-the-art methods on six real-world datasets. • COCOA provides actionable, plausible, sparse and diverse counterfactuals. • Decision costs are taken into account when generating counterfactuals. • The obtained counterfactuals improve cost savings. • The method is presented for MLPs, but other architectures can be used. [ABSTRACT FROM AUTHOR]

Feature importance and interaction are among the main issues in explainable artificial intelligence or interpretable machine learning. To measure feature importance and interaction, several methods, such as H-statistic and partial dependency, have been proposed. However, it is difficult to understand the practical implications of importance and interaction. In this paper, a new method for measuring feature importance and interaction is proposed. For the classification model, we observed correctly predicted cases in a predictive model and grouped them according to the characteristics of the cases. We derived a method for feature importance and interaction from group information. For the regression model, we grouped cases according to the change in the size of the prediction error. The proposed method supports the same rationale for feature importance and interaction. It also supports the decomposition of feature importance to feature power and feature interactions. To implement the proposed method, three visualization tools, including a feature interaction graph, are implemented. Through the proposed work, we can better understand the working mechanism of a predictive model. [ABSTRACT FROM AUTHOR]

To solve hard problems, AI relies on a variety of disciplines such as logic, probabilistic reasoning, machine learning and mathematical programming. Although it is widely accepted that solving real-world problems requires an integration amongst these, contemporary representation methodologies offer little support for this. In an attempt to alleviate this situation, we position and motivate a new declarative programming framework in this paper. We focus on the semantical foundations in service of providing abstractions of well-known problems such as SAT, Bayesian inference, generative models, learning and convex optimization. Programs are understood in terms of first-order logic structures with semiring labels, which allows us to freely combine and integrate problems from different AI disciplines and represent non-standard problems over unbounded domains. Thus, the main thrust of this paper is to view such well-known problems through a unified lens in the hope that appropriate solver strategies (exact, approximate, portfolio or hybrid) may emerge that tackle real-world problems in a principled way. [ABSTRACT FROM AUTHOR]

Purpose: Academic success and failure are relevant lifelines for economic success in the knowledge-based economy. The purpose of this paper is to predict the propensity of students' academic performance using early detection indicators (i.e. age, gender, high school exam scores, region, CGPA) to allow for timely and efficient remediation. Design/methodology/approach: A machine learning approach was used to develop a model based on secondary data obtained from students' information system in a Nigerian university. Findings: Results revealed that age is not a predictor for academic success (high CGPA); female students are 1.2 times more likely to have high CGPA compared to their male counterparts; students with high JAMB scores are more likely to achieve academic success, high CGPA and vice versa; students from affluent and developed regions are more likely to achieve academic success, high CGPA and vice versa; and students in Years 3 and 4 are more likely to achieve academic success, high CGPA. Originality/value: This predictive model serves as a classifier and useful strategy to mitigate failure, promote success and better manage resources in tertiary institutions. [ABSTRACT FROM AUTHOR]

Progress in the field of Non-Intrusive Load Monitoring (NILM) has been attributed to the rise in the application of artificial intelligence. Nevertheless, the ability of energy disaggregation algorithms to disaggregate different appliance signatures from aggregated smart grid data poses some privacy issues. This paper introduces a new notion of disclosure risk termed energy disaggregation risk. The performance of Sequence-to-Sequence (Seq2Seq) NILM deep learning algorithm along with three activation extraction methods are studied using two publicly available datasets. To understand the extent of disclosure, we study three inference attacks on aggregated data. The results show that Variance Sensitive Thresholding (VST) event detection method outperformed the other two methods in revealing households' lifestyles based on the signature of the appliances. To reduce energy disaggregation risk, we investigate the performance of two privacy-preserving mechanisms based on microaggregation and Discrete Fourier Transform (DFT). Empirically, for the first scenario of inference attack on UK-DALE, VST produces disaggregation risks of 99%, 100%, 89% and 99% for fridge, dish washer, microwave, and kettle respectively. For washing machine, Activation Time Extraction (ATE) method produces a disaggregation risk of 87%. We obtain similar results for other inference attack scenarios and the risk reduces using the two privacy-protection mechanisms. [ABSTRACT FROM AUTHOR]

Technology has grown rapidly in recent years, and new solutions that rely on Machine Learning (ML) and Artificial Intelligence (AI) are introduced every day. With such fast-paced advancement, inspecting and fully comprehending how given models make decisions is becoming problematic. The complex decision-making process of these models has become a black box, making it challenging to unravel how they work; therefore, eXplainable Artificial Intelligence (XAI) methods are crucial for further development. This paper discusses how state-of-the-art techniques determine classifications and why they need to be revised to understand the prediction-generating process fully. It compares those existing solutions with the new method called Principal Image Sections Mapping - PRISM, which relies on Principal Component Analysis and allows visualising the most significant features recognised by a given Convolutional Neural Network. PRISM is implemented in a piece of software called TorchPRISM that can generate and present the clustering based on the method's output. The result can indicate ambiguous classes discrimination; thus, the possibility of automating the output analysis process is also discussed. The paper's main objective is to examine how PRISM enhances the current understanding of the decision-making process and introduce a tool that can facilitate analysing the output. PRISM implementation (TorchPRISM) can be found in the public GitHub repository: https://github.com/szandala/TorchPRISM • PRISM method can explain CNN's decisions in an understandable way for various users. • PRISM uses PCA to point features and highlights them using an RGB-coloured image mask. • PRISM's effectiveness is assessed based on qualitative and quantitative measures. • TorchPRISM software allows the identification of ambiguous classes in large datasets. • PRISM overcomes the deficiencies of existing eXplainable AI and saliency map methods. [ABSTRACT FROM AUTHOR]

• The stochastic separation theorems are applied to develop industrial computer vision systems. • New class of algorithms are presented and verified for removing AI errors. • This class of algorithms is based on stochastic separation theorems combined with clustering. • The algorithms are tested on a relevant real-life problem. In this paper we present theory and algorithms enabling classes of Artificial Intelligence (AI) systems to continuously and incrementally improve with a priori quantifiable guarantees – or more specifically remove classification errors – over time. This is distinct from state-of-the-art machine learning, AI, and software approaches. The theory enables building few-shot AI correction algorithms and provides conditions justifying their successful application. Another feature of this approach is that, in the supervised setting, the computational complexity of training is linear in the number of training samples. At the time of classification, the computational complexity is bounded by few inner product calculations. Moreover, the implementation is shown to be very scalable. This makes it viable for deployment in applications where computational power and memory are limited, such as embedded environments. It enables the possibility for fast on-line optimisation using improved training samples. The approach is based on the concentration of measure effects and stochastic separation theorems and is illustrated with an example on the identification faulty processes in Computer Numerical Control (CNC) milling and with a case study on adaptive removal of false positives in an industrial video surveillance and analytics system. [ABSTRACT FROM AUTHOR]

Purpose: This paper provides an effective study to detect and locate the inter-turn short-circuit faults (ITSC) in a three-phase induction motor (IM) using the support vector machine (SVM). The characteristics extracted from the analysis of the phase shifts between the stator currents and their corresponding voltages are used as inputs to train the SVM. The latter automatically decides on the IM state, either a healthy motor or a short-circuit fault on one of its three phases. Design/methodology/approach: To evaluate the performance of the SVM, three supervised algorithms of machine learning, namely, multi-layer perceptron neural networks (MLPNNs), radial basis function neural networks (RBFNNs) and extreme learning machine (ELM) are used along with the SVM in this study. Thus, all classifiers (SVM, MLPNN, RBFNN and ELM) are tested and the results are compared with the same data set. Findings: The obtained results showed that the SVM outperforms MLPNN, RBFNNs and ELM to diagnose the health status of the IM. Especially, this technique (SVM) provides an excellent performance because it is able to detect a fault of two short-circuited turns (early detection) when the IM is operating under a low load. Originality/value: The original of this work is to use the SVM algorithm based on the phase shift between the stator currents and their voltages as inputs to detect and locate the ITSC fault. [ABSTRACT FROM AUTHOR]

This paper presents an extension of the reinforcement learning algorithms to design suboptimal control sequences for multiple performance functions in continuous-time systems. The first part of the paper provides the theoretical development and studies the required conditions to obtain a state-feedback control policy that achieves Pareto optimal results for the multiobjective performance vector. Then, a policy iteration algorithm is proposed that takes into account practical considerations to allow its implementation in real-time applications for systems with partially unknown models. Finally, the multiobjective linear quadratic regulator problem is solved using the proposed control scheme and employing a multiobjective optimization software to solve the static optimization problem at each iteration. [ABSTRACT FROM AUTHOR]

Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic appliances operating at low power. This paper discusses tradeoffs of selecting parameters of binary HD representations when applied to pattern recognition tasks. Particular design choices include density of representations and strategies for mapping data from the original representation. It is demonstrated that for the considered pattern recognition tasks (using synthetic and real-world data) both sparse and dense representations behave nearly identically. This paper also discusses implementation peculiarities which may favor one type of representations over the other. Finally, the capacity of representations of various densities is discussed. [ABSTRACT FROM AUTHOR]

Image caption is an important application field of artificial intelligence technique. When a machine can describe a picture reasonably like a human, it represents that the machine has higher intelligence to understand the picture. However, for complex machine learning tasks such as image caption, data annotation is time-consuming and laborious. Usually in a new application scenario, data annotation rarely results in poor model performance. A large number of easily available unlabeled image data make it possible to semi-supervised learning of image caption methods. Based on the existing end-to-end deep learning paradigm, a semi-supervised deep learning method is proposed in this paper, called N-gram + Pseudo Label NIC method. The method combines the current mainstream deep neural network method, e.g. the NIC (Neural Image Caption) model, and the semi-supervised deep learning idea of pseudo labels, and N-gram. This method generates pseudo labels by N-gram Search algorithm, and improves the effect of the model by utilizing the prior knowledge of the N-gram table and people's descriptive habits. This method has achieved better results than the original NIC model on different sub-data sets of Flickr 8K data set and MSCOCO data set of 0.5k, 1k, 2k and 3k under BLEU-1 evaluation criteria. [ABSTRACT FROM AUTHOR]

Accurate estimation of energy savings is crucial for the effective implementation of energy conservation measures (ECMs). Simultaneously, the integration of Artificial Intelligence (AI) has revolutionized software engineering by imbuing software with intelligent capabilities and autonomy. In this paper, we propose an ensemble model for precisely estimating baseline energy consumption within the realm of AI-empowered autonomous software. The ensemble model combines predictions from three tree-based Machine Learning models, namely Random Forest, XGBoost, and LightGBM. Notably, our model emphasizes the provision of explainability, granting transparency and insights into the key factors influencing baseline energy consumption. To validate its effectiveness, we conduct experimental evaluations on a diverse cluster of real-world buildings in Latvia. The results demonstrate the superiority of our proposed ensemble model over individual models and even a deep learning network tailored for energy consumption estimation. These findings underscore the efficacy of AI-empowered models in the energy sector, offering a robust and interpretable solution for estimating energy savings. [ABSTRACT FROM AUTHOR]

Machine learning has emerged as a promising paradigm to study the quantum dissipative dynamics of open quantum systems. To facilitate the use of our recently published ML-based approaches for quantum dissipative dynamics, here we present an open-source Python package MLQD (https://github.com/Arif-PhyChem/MLQD), which currently supports the three ML-based quantum dynamics approaches: (1) the recursive dynamics with kernel ridge regression (KRR) method, (2) the non-recursive artificial-intelligence-based quantum dynamics (AIQD) approach and (3) the blazingly fast one-shot trajectory learning (OSTL) approach, where both AIQD and OSTL use the convolutional neural networks (CNN). This paper describes the features of the MLQD package, the technical details, optimization of hyperparameters, visualization of results, and the demonstration of the MLQD 's applicability for two widely studied systems, namely the spin-boson model and the Fenna–Matthews–Olson (FMO) complex. To make MLQD more user-friendly and accessible, we have made it available on the Python Package Index (PyPi) platform and it can be installed via ▪. In addition, it is also available on the XACS cloud computing platform (https://XACScloud.com) via the interface to the MLatom package (http://MLatom.com). Program Title: MLQD CPC Library link to program files: https://doi.org/10.17632/yxp37csy5x.1 Developer's repository link: https://github.com/Arif-PhyChem/MLQD Code Ocean capsule: https://codeocean.com/capsule/5563143/tree Licensing provisions: Apache Software License 2.0 Programming language: Python 3.0 Supplementary material: Jupyter Notebook-based tutorials External routines/libraries: Tensorflow, Scikit-learn, Hyperopt, Matplotlib, MLatom Nature of problem: Fast propagation of quantum dissipative dynamics with machine learning approaches. Solution method: We have developed MLQD as a comprehensive framework that streamlines and supports the implementation of our recently published machine learning-based approaches for efficient propagation of quantum dissipative dynamics. This framework encompasses: (1) the recursive dynamics with kernel ridge regression (KRR) method, as well as the non-recursive approaches utilizing convolutional neural networks (CNN), namely (2) artificial intelligence-based quantum dynamics (AIQD), and (3) one-shot trajectory learning (OSTL). Additional comments including restrictions and unusual features: 1. Users can train a machine learning (ML) model following one of the ML-based approaches: KRR, AIQD and OSTL. 2. Users have the option to propagate dynamics with the existing trained ML models. 3. MLQD also provides the transformation of trajectories into the training data. 4. MLQD also supports hyperparameter optimization using MLATOM's grid search functionality for KRR and Bayesian methods with Tree-structured Parzen Estimator (TPE) for CNN models via the HYPEROPT package. 5. MLQD also facilitates the visualization of results via auto-plotting. 6. MLQD is designed to be user-friendly and easily accessible, with availability on the XACS cloud computing platform (https://XACScloud.com) via the interface to the MLATOM package (http://MLatom.com). In addition, it is also available as a pip package which makes it easy to install. Future outlook: MLQD will be extended to more realistic systems along with the incorporation of other machine learning-based approaches as well as the traditional quantum dynamics methods. [ABSTRACT FROM AUTHOR]

The recent studies present the various perspectives of Formal Concept Analysis from the Artificial Intelligence point of view since it can provide powerful techniques for knowledge representation, classification tasks, recommendation techniques, or data analysis. Formal Concept Analysis can be generally seen as an unsupervised Machine Learning technique that applies mathematical lattice theory to organize data based on objects and their shared attributes. However, the connections of Formal Concept Analysis with supervised learning are also thoroughly investigated. Regarding supervised learning, the learning algorithms of random forests or decision jungles have become popular and powerful Machine Learning ensemble methods. In this paper, we propose a generalization of a classification method based on the generalized decision directed acyclic graphs. We outline and review the recent studies on connections between Formal Concept Analysis and supervised learning. Finally, we present the results of our experiments regarding several datasets from the UCI Machine Learning repository. [ABSTRACT FROM AUTHOR]

In the first issue of Nature 2015, Google DeepMind published a paper “Human-level control through deep reinforcement learning.” Furthermore, in the first issue of Nature 2016, it published a cover paper “Mastering the game of Go with deep neural networks and tree search” and proposed the computer Go program, AlphaGo. In March 2016, AlphaGo beat the world’s top Go player Lee Sedol by 4:1. This becomes a new milestone in artificial intelligence history, the core of which is the algorithm of deep reinforcement learning (RL). [ABSTRACT FROM AUTHOR]

Time series are a kind of streaming data, which are chaotic and sequential. As real-world time series data are often not available at once and drift with time growth, Incremental Learning (IL) is well suited for Time Series Prediction (TSP). Most previous incremental TSP algorithms are limited by the assumption of data balance. However, real-world time series data are often unbalanced, with long-tailed distribution and other characteristics resulting in the failure of IL algorithms. In this paper, a balanced-driven Active Learning (AL) strategy is proposed to deal with data imbalance problems in IL processes. What's more, by integrating the advantages of Deep Learning (DL) and the Broad Learning System (BLS), a novel Deep-Broad Learning (DeepBL) network with its incremental learning algorithm is proposed. The proposed A ctive Learning-based I ncremental Deep - B road L earning (AI_DeepBL) algorithm is applied to real-world univariate and multivariate time series datasets and achieves superior performance compared with classical and state-of-the-art TSP algorithms. [ABSTRACT FROM AUTHOR]

Anticipating price crises in the market of agri-commodities is critical to guarantee both the sustainability of the food system and to ensure food security. However, this is not an easy task, since the problem implies analyzing small and very volatile time series, which are highly influenced by external factors. In this paper, we show that suitable reservoir computing algorithms can be developed that outperform traditional approaches, by reducing the Mean Absolute Error and, more importantly, increasing the Market Direction Accuracy. For this purpose, the applicability of five variants of such method to forecast this market is explored, and their performance evaluated by comparing the results with those obtained with the standard LSTM and SARIMA benchmarks. We conclude that decomposing the time series and modeling each component with a separate RC is essential to successfully anticipate price trends, and that this method works even in the complex changing temporal scenario of the Covid-19 pandemic, when part of the data were collected. • We tackle current food loss problem. • Explore predictability in agri-food market. • Successfully anticipate sudden price crisis. • Use the recent ML Reservoir Computing method. • We outperform traditional benchmark models: SARIMA and LSTM. [ABSTRACT FROM AUTHOR]

In this paper, we consider the composition optimization with two expected-value functions in the form of $({1}/{n})\sum _{i = 1}^{n} F_{i}\left({({1}/{m})\sum _{j = 1}^{m} G_{j}(x)}\right)+R(x)$ , which formulates many important problems in statistical learning and machine learning such as solving Bellman equations in reinforcement learning and nonlinear embedding. Full gradient- or classical stochastic gradient descent-based optimization algorithms are unsuitable or computationally expensive to solve this problem due to the inner expectation $({1}/{m})\sum _{j = 1}^{m} G_{j}(x)$. We propose a dualityfree-based stochastic composition method that combines the variance reduction methods to address the stochastic composition problem. We apply the stochastic variance reduction gradient- and stochastic average gradient algorithm-based methods to estimate the inner function and the dualityfree method to estimate the outer function. We prove the linear convergence rate not only for the convex composition problem but also for the case that the individual outer functions are nonconvex, while the objective function is strongly convex. We also provide the results of experiments that show the effectiveness of our proposed methods. [ABSTRACT FROM AUTHOR]

Most feature selection methods first compute a similarity matrix by assigning a fixed value to pairs of objects in the whole data or to pairs of objects in a class or by computing the similarity between two objects from the original data. The similarity matrix is fixed as a constant in the subsequent feature selection process. However, the similarities computed from the original data may be unreliable, because they are affected by noise features. Moreover, the local structure within classes cannot be recovered if the similarities between the pairs of objects in a class are equal. In this paper, we propose a novel local adaptive projection (LAP) framework. Instead of computing fixed similarities before performing feature selection, LAP simultaneously learns an adaptive similarity matrix $\mathbf{S}$ and a projection matrix $\mathbf{W}$ with an iterative method. In each iteration, $\mathbf{S}$ is computed from the projected distance with the learned $\mathbf{W}$ and W is computed with the learned $\mathbf{S}$. Therefore, LAP can learn better projection matrix $\mathbf{W}$ by weakening the effect of noise features with the adaptive similarity matrix. A supervised feature selection with LAP (SLAP) method and an unsupervised feature selection with LAP (ULAP) method are proposed. Experimental results on eight data sets show the superiority of SLAP compared with seven supervised feature selection methods and the superiority of ULAP compared with five unsupervised feature selection methods. [ABSTRACT FROM AUTHOR]

The pervasiveness of wearable devices furnished with state-of-the-art sensors has shown the powerful capability in context-aware applications. However, embedded sensors also become targets for adversaries to launch potential side-channel attacks. In this paper, we present a self-adaptive and pretraining-independent pattern attack that infers a graphical password by recovering the victim’s hand movement trajectory via motion sensors of a wrist-worn smart device. With the adaptive pattern inference algorithm, the discovered attack can be launched remotely without requiring previous training data from victims or the prior knowledge about the keyboard input settings. Toward the proposed attack, we create a method to detect the sliding behavior that draws a graphical password on the screen. We also propose an inference algorithm to generate password candidates from hand movement trajectories for different keypad input settings. We implement the discovered attack on a smartwatch and conduct experiments to evaluate the impact of this attack. The evaluation results show that for complex graphical patterns, with a single try, the attack can infer the passwords at a success rate as high as 80%, and the success rate can be further boosted to over 90% within five attempts, which reveals the overlooked privacy information threat caused by sensor data leakage. [ABSTRACT FROM AUTHOR]

In this paper, kurtosis-based complex-valued real-time recurrent learning (KCRTRL) and kurtosis-based augmented CRTRL (KACRTRL) algorithms are proposed for training fully connected recurrent neural networks (FCRNNs) in the complex domain. These algorithms are designed by minimizing the cost functions based on the kurtosis of a complex-valued error signal. The KCRTRL algorithm exploits the circularity properties of the complex-valued signals, and this algorithm not only provides a faster convergence rate but also results in a lower steady-state error. However, the KCRTRL algorithm is suboptimal in the processing of noncircular (NC) complex-valued signals. On the other hand, the KACRTRL algorithm contains a complete second-order information due to the augmented statistics, thus considerably improves the performance of the FCRNN in the processing of NC complex-valued signals. Simulation results on the one-step-ahead prediction problems show that the proposed KCRTRL algorithm significantly enhances the performance for only circular complex-valued signals, whereas the proposed KACRTRL algorithm provides more superior performance than existing algorithms for NC complex-valued signals in terms of the convergence rate and the steady-state error. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have become a key element in the recent breakthrough of salient object detection. However, existing CNN-based methods are based on either patchwise (regionwise) training and inference or fully convolutional networks. Methods in the former category are generally time-consuming due to severe storage and computational redundancies among overlapping patches. To overcome this deficiency, methods in the second category attempt to directly map a raw input image to a predicted dense saliency map in a single network forward pass. Though being very efficient, it is arduous for these methods to detect salient objects of different scales or salient regions with weak semantic information. In this paper, we develop hybrid contrast-oriented deep neural networks to overcome the aforementioned limitations. Each of our deep networks is composed of two complementary components, including a fully convolutional stream for dense prediction and a segment-level spatial pooling stream for sparse saliency inference. We further propose an attentional module that learns weight maps for fusing the two saliency predictions from these two streams. A tailored alternate scheme is designed to train these deep networks by fine-tuning pretrained baseline models. Finally, a customized fully connected conditional random field model incorporating a salient contour feature embedding can be optionally applied as a postprocessing step to improve spatial coherence and contour positioning in the fused result from these two streams. Extensive experiments on six benchmark data sets demonstrate that our proposed model can significantly outperform the state of the art in terms of all popular evaluation metrics. [ABSTRACT FROM AUTHOR]

Nowadays, the control technology of the robotic manipulator with flexible joints (RMFJ) is not mature enough. The flexible-joint manipulator dynamic system possesses many uncertainties, which brings a great challenge to the controller design. This paper is motivated by this problem. In order to deal with this and enhance the system robustness, the full-state feedback neural network (NN) control is proposed. Moreover, output constraints of the RMFJ are achieved, which improve the security of the robot. Through the Lyapunov stability analysis, we identify that the proposed controller can guarantee not only the stability of flexible-joint manipulator system but also the boundedness of system state variables by choosing appropriate control gains. Then, we make some necessary simulation experiments to verify the rationality of our controllers. Finally, a series of control experiments are conducted on the Baxter. By comparing with the proportional–derivative control and the NN control with the rigid manipulator model, the feasibility and the effectiveness of NN control based on flexible-joint manipulator model are verified. [ABSTRACT FROM AUTHOR]

In this paper, we present an approach for minimizing the computational complexity of the trained convolutional neural networks (ConvNets). The idea is to approximate all elements of a given ConvNet and replace the original convolutional filters and parameters (pooling and bias coefficients; and activation function) with an efficient approximations capable of extreme reductions in computational complexity. Low-complexity convolution filters are obtained through a binary (zero and one) linear programming scheme based on the Frobenius norm over sets of dyadic rationals. The resulting matrices allow for multiplication-free computations requiring only addition and bit-shifting operations. Such low-complexity structures pave the way for low power, efficient hardware designs. We applied our approach on three use cases of different complexities: 1) a “light” but efficient ConvNet for face detection (with around 1000 parameters); 2) another one for hand-written digit classification (with more than 180 000 parameters); and 3) a significantly larger ConvNet: AlexNet with $\approx 1.2$ million matrices. We evaluated the overall performance on the respective tasks for different levels of approximations. In all considered applications, very low-complexity approximations have been derived maintaining an almost equal classification performance. [ABSTRACT FROM AUTHOR]

This paper focuses on the event-triggered guaranteed cost control design of nonlinear systems via a self-learning technique. In brief, an event-based guaranteed cost control strategy of nonlinear systems subjects to matched uncertainties is developed, thereby balancing the performance of guaranteed cost and the actuality of limited communication resource. The original control design is transformed into an optimal control problem with an event-based mechanism, where the relationship of guaranteed cost performance compared to the time-based formulation is discussed. A critic neural network is constructed for implementing the event-based optimal control design with stability guarantee. Simulation experiments are carried out to verify the theoretical results in detail. [ABSTRACT FROM AUTHOR]

The robust Huber’s M-estimator is widely used in signal and image processing, classification, and regression. From an optimization point of view, Huber’s M-estimation problem is often formulated as a large-sized quadratic programming (QP) problem in view of its nonsmooth cost function. This paper presents a generalized regression estimator which minimizes a reduced-sized QP problem. The generalized regression estimator may be viewed as a significant generalization of several robust regression estimators including Huber’s M-estimator. The performance of the generalized regression estimator is analyzed in terms of robustness and approximation accuracy. Furthermore, two low-dimensional recurrent neural networks (RNNs) are introduced for robust estimation. The two RNNs have low model complexity and enhanced computational efficiency. Finally, the experimental results of two examples and an application to image restoration are presented to substantiate superior performance of the proposed method over conventional algorithms for robust regression estimation in terms of approximation accuracy and convergence rate. [ABSTRACT FROM AUTHOR]

An intelligent data-driven predictive control strategy is proposed in this paper. The predictive controller is designed by combining predictive control and local weighted projection regression. The presented control strategy needs less prior knowledge and has fewer parameters that are hard to determine compared to other data-driven predictive controller, e.g., the one in dynamic partial least square (PLS) framework. Furthermore, the proposed predictive controller performs better in the control of nonlinear processes and is able to update its parameters based on the online data. The predictive model validity and intelligence of the control strategy are guaranteed by the online updating strategy to a certain degree. The control performance of the proposed predictive controller against the model predictive control (MPC) in dynamic PLS framework is illustrated through the simulation of a typical numerical example and the benchmark of a continuous stirred tank heater system. It can be observed from the simulation that the proposed MPC strategy has higher prediction precision and stronger ability in coping with nonlinear dynamic processes which are quite common in practical applications, for instance, the industrial process. [ABSTRACT FROM AUTHOR]

Image captioning aims to generate natural language sentences to describe the salient parts of a given image. Although neural networks have recently achieved promising results, a key problem is that they can only describe concepts seen in the training image-sentence pairs. Efficient learning of novel concepts has thus been a topic of recent interest to alleviate the expensive manpower of labeling data. In this paper, we propose a novel method,Image-Text Surgery, to synthesize pseudoimage-sentence pairs. The pseudopairs are generated under the guidance of a knowledge base, with syntax from a seed data set (i.e., MSCOCO) and visual information from an existing large-scale image base (i.e., ImageNet). Via pseudodata, the captioning model learns novel concepts without any corresponding human-labeled pairs. We further introduce adaptive visual replacement, which adaptively filters unnecessary visual features in pseudodata with an attention mechanism. We evaluate our approach on a held-out subset of the MSCOCO data set. The experimental results demonstrate that the proposed approach provides significant performance improvements over state-of-the-art methods in terms of F1 score and sentence quality. An ablation study and the qualitative results further validate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Learning discriminative feature representations has shown remarkable importance due to its promising performance for machine learning problems. This paper presents a discriminative data representation learning framework by employing a simple yet powerful marginal regression function with probabilistic graphical structure adaptation. A marginally structured representation learning (MSRL) method is proposed by seamlessly incorporating distinguishable regression targets analysis, graph structure adaptation, and robust linear structural learning into a joint framework. Specifically, MSRL learns marginal regression targets from data rather than exploiting the conventional zero–one matrix that greatly hinders the freedom of regression fitness and degrades the performance of regression results. Meanwhile, an optimized graph regularization term with self-improving adaptation is constructed based on probabilistic connection knowledge to improve the compactness of the learned representation. Additionally, the regression targets are further predicted by utilizing the explanatory factors from the latent subspace of data, which can uncover the underlying feature correlations to enhance the reliability. The resulting optimization problem can be elegantly solved by an efficient iterative algorithm. Finally, the proposed method is evaluated by eight diverse but related tasks, including object, face, texture, and scene, categorization data sets. The encouraging experimental results and the explicit theoretical analysis demonstrate the efficacy of the proposed representation learning method in comparison with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

This paper reviews the current state of the art on reinforcement learning (RL)-based feedback control solutions to optimal regulation and tracking of single and multiagent systems. Existing RL solutions to both optimal \mathcal H2 and \mathcal H_\infty control problems, as well as graphical games, will be reviewed. RL methods learn the solution to optimal control and game problems online and using measured data along the system trajectories. We discuss Q-learning and the integral RL algorithm as core algorithms for discrete-time (DT) and continuous-time (CT) systems, respectively. Moreover, we discuss a new direction of off-policy RL for both CT and DT systems. Finally, we review several applications. [ABSTRACT FROM AUTHOR]

In this paper, a new training paradigm is proposed for deep reinforcement learning using self-paced prioritized curriculum learning with coverage penalty. The proposed deep curriculum reinforcement learning (DCRL) takes the most advantage of experience replay by adaptively selecting appropriate transitions from replay memory based on the complexity of each transition. The criteria of complexity in DCRL consist of self-paced priority as well as coverage penalty. The self-paced priority reflects the relationship between the temporal-difference error and the difficulty of the current curriculum for sample efficiency. The coverage penalty is taken into account for sample diversity. With comparison to deep Q network (DQN) and prioritized experience replay (PER) methods, the DCRL algorithm is evaluated on Atari 2600 games, and the experimental results show that DCRL outperforms DQN and PER on most of these games. More results further show that the proposed curriculum training paradigm of DCRL is also applicable and effective for other memory-based deep reinforcement learning approaches, such as double DQN and dueling network. All the experimental results demonstrate that DCRL can achieve improved training efficiency and robustness for deep reinforcement learning. [ABSTRACT FROM AUTHOR]