Search

Discovering a suitable neural network architecture for modeling complex dynamical systems poses a formidable challenge, often involving extensive trial and error and navigation through a high-dimensional hyper-parameter space. In this paper, we discuss a systematic approach to constructing neural architectures for modeling a subclass of dynamical systems, namely, Linear Time-Invariant (LTI) systems. We use a variant of continuous-time neural networks in which the output of each neuron evolves continuously as a solution of a first-order or second-order Ordinary Differential Equation (ODE). Instead of deriving the network architecture and parameters from data, we propose a gradient-free algorithm to compute sparse architecture and network parameters directly from the given LTI system, leveraging its properties. We bring forth a novel neural architecture paradigm featuring horizontal hidden layers and provide insights into why employing conventional neural architectures with vertical hidden layers may not be favorable. We also provide an upper bound on the numerical errors of our neural networks. Finally, we demonstrate the high accuracy of our constructed networks on three numerical examples., Comment: 37 pages, 25 figures

We characterize the computational power of neural networks that follow the graph neural network (GNN) architecture, not restricted to aggregate-combine GNNs or other particular types. We establish an exact correspondence between the expressivity of GNNs using diverse activation functions and arithmetic circuits over real numbers. In our results the activation function of the network becomes a gate type in the circuit. Our result holds for families of constant depth circuits and networks, both uniformly and non-uniformly, for all common activation functions.

The ability of zero-shot translation emerges when we train a multilingual model with certain translation directions; the model can then directly translate in unseen directions. Alternatively, zero-shot translation can be accomplished by pivoting through a third language (e.g., English). In our work, we observe that both direct and pivot translations are noisy and achieve less satisfactory performance. We propose EBBS, an ensemble method with a novel bi-level beam search algorithm, where each ensemble component explores its own prediction step by step at the lower level but they are synchronized by a "soft voting" mechanism at the upper level. Results on two popular multilingual translation datasets show that EBBS consistently outperforms direct and pivot translations as well as existing ensemble techniques. Further, we can distill the ensemble's knowledge back to the multilingual model to improve inference efficiency; profoundly, our EBBS-based distillation does not sacrifice, or even improves, the translation quality.

The burgeoning integration of artificial intelligence (AI) into human society brings forth significant implications for societal governance and safety. While considerable strides have been made in addressing AI alignment challenges, existing methodologies primarily focus on technical facets, often neglecting the intricate sociotechnical nature of AI systems, which can lead to a misalignment between the development and deployment contexts. To this end, we posit a new problem worth exploring: Incentive Compatibility Sociotechnical Alignment Problem (ICSAP). We hope this can call for more researchers to explore how to leverage the principles of Incentive Compatibility (IC) from game theory to bridge the gap between technical and societal components to maintain AI consensus with human societies in different contexts. We further discuss three classical game problems for achieving IC: mechanism design, contract theory, and Bayesian persuasion, in addressing the perspectives, potentials, and challenges of solving ICSAP, and provide preliminary implementation conceptions., Comment: 13 pages, 2 figures

Error Feedback (EF) is a highly popular and immensely effective mechanism for fixing convergence issues which arise in distributed training methods (such as distributed GD or SGD) when these are enhanced with greedy communication compression techniques such as TopK. While EF was proposed almost a decade ago (Seide et al., 2014), and despite concentrated effort by the community to advance the theoretical understanding of this mechanism, there is still a lot to explore. In this work we study a modern form of error feedback called EF21 (Richtarik et al., 2021) which offers the currently best-known theoretical guarantees, under the weakest assumptions, and also works well in practice. In particular, while the theoretical communication complexity of EF21 depends on the quadratic mean of certain smoothness parameters, we improve this dependence to their arithmetic mean, which is always smaller, and can be substantially smaller, especially in heterogeneous data regimes. We take the reader on a journey of our discovery process. Starting with the idea of applying EF21 to an equivalent reformulation of the underlying problem which (unfortunately) requires (often impractical) machine cloning, we continue to the discovery of a new weighted version of EF21 which can (fortunately) be executed without any cloning, and finally circle back to an improved analysis of the original EF21 method. While this development applies to the simplest form of EF21, our approach naturally extends to more elaborate variants involving stochastic gradients and partial participation. Further, our technique improves the best-known theory of EF21 in the rare features regime (Richtarik et al., 2023). Finally, we validate our theoretical findings with suitable experiments., Comment: 70 pages, 14 figures, 6 tables

The performance of an artificial neural network (ANN) in forecasting crash risk is shown in this paper. To begin, some traffic and weather data are acquired as raw data. This data is then analyzed, and relevant characteristics are chosen to utilize as input data based on additional tree and Pearson correlation. Furthermore, crash and non-crash time data are separated; then, feature values for crash and non-crash events are written in three four-minute intervals prior to the crash and non-crash events using the average of all available values for that period. The number of non-crash samples was lowered after calculating crash likelihood for each period based on accident labeling. The proposed CNN model is capable of learning from recorded, processed, and categorized input characteristics such as traffic characteristics and meteorological conditions. The goal of this work is to forecast the chance of a real-time crash based on three periods before events. The area under the curve (AUC) for the receiver operating characteristic curve (ROC curve), as well as sensitivity as the true positive rate and specificity as the false positive rate, are shown and compared with three typical machine learning and neural network models. Finally, when it comes to the error value, AUC, sensitivity, and specificity parameters as performance variables, the executed model outperforms other models. The findings of this research suggest applying the CNN model as a multi-class prediction model for real-time crash risk prediction. Our emphasis is on multi-class prediction, while prior research used this for binary (two-class) categorization like crash and non-crash., Comment: 17 pages, 16 figures

In the evolving field of machine learning, ensuring fairness has become a critical concern, prompting the development of algorithms designed to mitigate discriminatory outcomes in decision-making processes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time while another does not, leading to a decrease in fairness even if accuracy remains fairly stable. Within the framework of federated learning, where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. One of the significant contributions of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the realm of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift which utilizes a multi-model approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.

This paper presents a novel approach at the intersection of machine learning and number theory, focusing on the classification of prime and non-prime numbers. At the core of our research is the development of a highly sparse encoding method, integrated with conventional neural network architectures. This combination has shown promising results, achieving a recall of over 99\% in identifying prime numbers and 79\% for non-prime numbers from an inherently imbalanced sequential series of integers, while exhibiting rapid model convergence before the completion of a single training epoch. We performed training using $10^6$ integers starting from a specified integer and tested on a different range of $2 \times 10^6$ integers extending from $10^6$ to $3 \times 10^6$, offset by the same starting integer. While constrained by the memory capacity of our resources, which limited our analysis to a span of $3\times10^6$, we believe that our study contribute to the application of machine learning in prime number analysis. This work aims to demonstrate the potential of such applications and hopes to inspire further exploration and possibilities in diverse fields.

Artificial intelligence (AI) has acquired notorious relevance in modern computing as it effectively solves complex tasks traditionally done by humans. AI provides methods to represent and infer knowledge, efficiently manipulate texts and learn from vast amount of data. These characteristics are applicable in many activities that human find laborious or repetitive, as is the case of the analysis of scientific literature. Manually preparing and writing a systematic literature review (SLR) takes considerable time and effort, since it requires planning a strategy, conducting the literature search and analysis, and reporting the findings. Depending on the area under study, the number of papers retrieved can be of hundreds or thousands, meaning that filtering those relevant ones and extracting the key information becomes a costly and error-prone process. However, some of the involved tasks are repetitive and, therefore, subject to automation by means of AI. In this paper, we present a survey of AI techniques proposed in the last 15 years to help researchers conduct systematic analyses of scientific literature. We describe the tasks currently supported, the types of algorithms applied, and available tools proposed in 34 primary studies. This survey also provides a historical perspective of the evolution of the field and the role that humans can play in an increasingly automated SLR process., Comment: 25 pages, 3 figures, 1 table, journal paper

Computer-based scene understanding has influenced fields ranging from urban planning to autonomous vehicle performance, yet little is known about how well these technologies work across social differences. We investigate the biases of deep convolutional neural networks (dCNNs) in scene classification, using nearly one million images from global and US sources, including user-submitted home photographs and Airbnb listings. We applied statistical models to quantify the impact of socioeconomic indicators such as family income, Human Development Index (HDI), and demographic factors from public data sources (CIA and US Census) on dCNN performance. Our analyses revealed significant socioeconomic bias, where pretrained dCNNs demonstrated lower classification accuracy, lower classification confidence, and a higher tendency to assign labels that could be offensive when applied to homes (e.g., "ruin", "slum"), especially in images from homes with lower socioeconomic status (SES). This trend is consistent across two datasets of international images and within the diverse economic and racial landscapes of the United States. This research contributes to understanding biases in computer vision, emphasizing the need for more inclusive and representative training datasets. By mitigating the bias in the computer vision pipelines, we can ensure fairer and more equitable outcomes for applied computer vision, including home valuation and smart home security systems. There is urgency in addressing these biases, which can significantly impact critical decisions in urban development and resource allocation. Our findings also motivate the development of AI systems that better understand and serve diverse communities, moving towards technology that equitably benefits all sectors of society., Comment: 20 pages, 3 figures, 3 tables

As Artificial Intelligence (AI) technology becomes more and more prevalent, it becomes increasingly important to explore how we as humans interact with AI. The Human-AI Interaction (HAI) sub-field has emerged from the Human-Computer Interaction (HCI) field and aims to examine this very notion. Many interaction patterns have been implemented without fully understanding the changes in required cognition as well as the cognitive science implications of using these alternative interfaces that aim to be more human-like in nature. Prior research suggests that theory of mind representations are crucial to successful and effortless communication, however very little is understood when it comes to how theory of mind representations are established when interacting with AI., Comment: 6 pages, 12 figures, 12 data tables, study data included in appendix

While the operationalisation of high-level AI ethics principles into practical AI/ML systems has made progress, there is still a theory-practice gap in managing tensions between the underlying AI ethics aspects. We cover five approaches for addressing the tensions via trade-offs, ranging from rudimentary to complex. The approaches differ in the types of considered context, scope, methods for measuring contexts, and degree of justification. None of the approaches is likely to be appropriate for all organisations, systems, or applications. To address this, we propose a framework which consists of: (i) proactive identification of tensions, (ii) prioritisation and weighting of ethics aspects, (iii) justification and documentation of trade-off decisions. The proposed framework aims to facilitate the implementation of well-rounded AI/ML systems that are appropriate for potential regulatory requirements.

Infinitely repeated games can support cooperative outcomes that are not equilibria in the one-shot game. The idea is to make sure that any gains from deviating will be offset by retaliation in future rounds. However, this model of cooperation fails in anonymous settings with many strategic agents that interact in pairs. Here, a player can defect and then avoid penalization by immediately switching partners. In this paper, we focus on a specific set of equilibria that avoids this pitfall. In them, agents follow a designated sequence of actions, and restart if their opponent ever deviates. We show that the socially-optimal sequence of actions consists of an infinitely repeating goal value, preceded by a hazing period. We introduce an equivalence relation on sequences and prove that the computational problem of finding a representative from the optimal equivalence class is (weakly) NP-hard. Nevertheless, we present a pseudo-polynomial time dynamic program for this problem, as well as an integer linear program, and show they are efficient in practice. Lastly, we introduce a fully polynomial-time approximation scheme that outputs a hazing sequence with arbitrarily small approximation ratio., Comment: 13 pages, 2 figures, main body to be published in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24), Jeju, South Korea, 2024

Air pollution poses a significant threat to public health and well-being, particularly in urban areas. This study introduces a series of machine-learning models that integrate data from the Sentinel-5P satellite, meteorological conditions, and topological characteristics to forecast future levels of five major pollutants. The investigation delineates the process of data collection, detailing the combination of diverse data sources utilized in the study. Through experiments conducted in the Milan metropolitan area, the models demonstrate their efficacy in predicting pollutant levels for the forthcoming day, achieving a percentage error of around 30%. The proposed models are advantageous as they are independent of monitoring stations, facilitating their use in areas without existing infrastructure. Additionally, we have released the collected dataset to the public, aiming to stimulate further research in this field. This research contributes to advancing our understanding of urban air quality dynamics and emphasizes the importance of amalgamating satellite, meteorological, and topographical data to develop robust pollution forecasting models., Comment: 5 pages, 2 figures, submitted to IEEE MetroLivEnv 2024

Selecting language models in business contexts requires a careful analysis of the final financial benefits of the investment. However, the emphasis of academia and industry analysis of LLM is solely on performance. This work introduces a framework to evaluate LLMs, focusing on the earnings and return on investment aspects that should be taken into account in business decision making. We use a decision-theoretic approach to compare the financial impact of different LLMs, considering variables such as the cost per token, the probability of success in the specific task, and the gain and losses associated with LLMs use. The study reveals how the superior accuracy of more expensive models can, under certain conditions, justify a greater investment through more significant earnings but not necessarily a larger RoI. This article provides a framework for companies looking to optimize their technology choices, ensuring that investment in cutting-edge technology aligns with strategic financial objectives. In addition, we discuss how changes in operational variables influence the economics of using LLMs, offering practical insights for enterprise settings, finding that the predicted gain and loss and the different probabilities of success and failure are the variables that most impact the sensitivity of the models., Comment: 27 pages, 13 figures

The expansion of streaming media and e-commerce has led to a boom in recommendation systems, including Sequential recommendation systems, which consider the user's previous interactions with items. In recent years, research has focused on architectural improvements such as transformer blocks and feature extraction that can augment model information. Among these features are context and attributes. Of particular importance is the temporal footprint, which is often considered part of the context and seen in previous publications as interchangeable with positional information. Other publications use positional encodings with little attention to them. In this paper, we analyse positional encodings, showing that they provide relative information between items that are not inferable from the temporal footprint. Furthermore, we evaluate different encodings and how they affect metrics and stability using Amazon datasets. We added some new encodings to help with these problems along the way. We found that we can reach new state-of-the-art results by finding the correct positional encoding, but more importantly, certain encodings stabilise the training., Comment: 19 pages, 3 figures, 12 tables

Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, such as helping to commit crimes or producing racist text. One approach to fine-tuning, called reinforcement learning from human feedback, learns from humans' expressed preferences over multiple outputs. Another approach is constitutional AI, in which the input from humans is a list of high-level principles. But how do we deal with potentially diverging input from humans? How can we aggregate the input into consistent data about "collective" preferences or otherwise use it to make collective choices about model behavior? In this paper, we argue that the field of social choice is well positioned to address these questions, and we discuss ways forward for this agenda, drawing on discussions in a recent workshop on Social Choice for AI Ethics and Safety held in Berkeley, CA, USA in December 2023., Comment: 15 pages, 4 figures

In recent years, large-scale adoption of cloud storage solutions has revolutionized the way we think about digital data storage. However, the exponential increase in data volume, especially images, has raised environmental concerns regarding power and resource consumption, as well as the rising digital carbon footprint emissions. The aim of this research is to propose a methodology for cloud-based image storage by integrating image compression technology with SuperResolution Generative Adversarial Networks (SRGAN). Rather than storing images in their original format directly on the cloud, our approach involves initially reducing the image size through compression and downsizing techniques before storage. Upon request, these compressed images will be retrieved and processed by SRGAN to generate images. The efficacy of the proposed method is evaluated in terms of PSNR and SSIM metrics. Additionally, a mathematical analysis is given to calculate power consumption and carbon footprint assesment. The proposed data compression technique provides a significant solution to achieve a reasonable trade off between environmental sustainability and industrial efficiency., Comment: 5 pages, 5 figures

Nasogastric tubes (NGTs) are feeding tubes that are inserted through the nose into the stomach to deliver nutrition or medication. If not placed correctly, they can cause serious harm, even death to patients. Recent AI developments demonstrate the feasibility of robustly detecting NGT placement from Chest X-ray images to reduce risks of sub-optimally or critically placed NGTs being missed or delayed in their detection, but gaps remain in clinical practice integration. In this study, we present a human-centered approach to the problem and describe insights derived following contextual inquiry and in-depth interviews with 15 clinical stakeholders. The interviews helped understand challenges in existing workflows, and how best to align technical capabilities with user needs and expectations. We discovered the trade-offs and complexities that need consideration when choosing suitable workflow stages, target users, and design configurations for different AI proposals. We explored how to balance AI benefits and risks for healthcare staff and patients within broader organizational and medical-legal constraints. We also identified data issues related to edge cases and data biases that affect model training and evaluation; how data documentation practices influence data preparation and labelling; and how to measure relevant AI outcomes reliably in future evaluations. We discuss how our work informs design and development of AI applications that are clinically useful, ethical, and acceptable in real-world healthcare services.

We introduce an innovative, simple, effective segmentation-free approach for outcome prediction in head \& neck cancer (HNC) patients. By harnessing deep learning-based feature extraction techniques and multi-angle maximum intensity projections (MA-MIPs) applied to Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) volumes, our proposed method eliminates the need for manual segmentations of regions-of-interest (ROIs) such as primary tumors and involved lymph nodes. Instead, a state-of-the-art object detection model is trained to perform automatic cropping of the head and neck region on the PET volumes. A pre-trained deep convolutional neural network backbone is then utilized to extract deep features from MA-MIPs obtained from 72 multi-angel axial rotations of the cropped PET volumes. These deep features extracted from multiple projection views of the PET volumes are then aggregated and fused, and employed to perform recurrence-free survival analysis on a cohort of 489 HNC patients. The proposed approach outperforms the best performing method on the target dataset for the task of recurrence-free survival analysis. By circumventing the manual delineation of the malignancies on the FDG PET-CT images, our approach eliminates the dependency on subjective interpretations and highly enhances the reproducibility of the proposed survival analysis method., Comment: 15 pages, 4 tables, 4 figures. Submitted for European Journal of Nuclear Medicine and Medical Imaging

The emerging research shows that lncRNAs are associated with a series of complex human diseases. However, most of the existing methods have limitations in identifying nonlinear lncRNA-disease associations (LDAs), and it remains a huge challenge to predict new LDAs. Therefore, the accurate identification of LDAs is very important for the warning and treatment of diseases. In this work, multiple sources of biomedical data are fully utilized to construct characteristics of lncRNAs and diseases, and linear and nonlinear characteristics are effectively integrated. Furthermore, a novel deep learning model based on graph attention automatic encoder is proposed, called HGATELDA. To begin with, the linear characteristics of lncRNAs and diseases are created by the miRNA-lncRNA interaction matrix and miRNA-disease interaction matrix. Following this, the nonlinear features of diseases and lncRNAs are extracted using a graph attention auto-encoder, which largely retains the critical information and effectively aggregates the neighborhood information of nodes. In the end, LDAs can be predicted by fusing the linear and nonlinear characteristics of diseases and lncRNA. The HGATELDA model achieves an impressive AUC value of 0.9692 when evaluated using a 5-fold cross-validation indicating its superior performance in comparison to several recent prediction models. Meanwhile, the effectiveness of HGATELDA in identifying novel LDAs is further demonstrated by case studies. the HGATELDA model appears to be a viable computational model for predicting LDAs., Comment: 10 pages, 8 figures

Despite the remarkable success of Large Language Models (LLMs) in text understanding and generation, their potential for text clustering tasks remains underexplored. We observed that powerful closed-source LLMs provide good quality clusterings of entity sets but are not scalable due to the massive compute power required and the associated costs. Thus, we propose CACTUS (Context-Aware ClusTering with aUgmented triplet losS), a systematic approach that leverages open-source LLMs for efficient and effective supervised clustering of entity subsets, particularly focusing on text-based entities. Existing text clustering methods fail to effectively capture the context provided by the entity subset. Moreover, though there are several language modeling based approaches for clustering, very few are designed for the task of supervised clustering. This paper introduces a novel approach towards clustering entity subsets using LLMs by capturing context via a scalable inter-entity attention mechanism. We propose a novel augmented triplet loss function tailored for supervised clustering, which addresses the inherent challenges of directly applying the triplet loss to this problem. Furthermore, we introduce a self-supervised clustering task based on text augmentation techniques to improve the generalization of our model. For evaluation, we collect ground truth clusterings from a closed-source LLM and transfer this knowledge to an open-source LLM under the supervised clustering framework, allowing a faster and cheaper open-source model to perform the same task. Experiments on various e-commerce query and product clustering datasets demonstrate that our proposed approach significantly outperforms existing unsupervised and supervised baselines under various external clustering evaluation metrics., Comment: 16 pages

Quantum machine learning (QML) is a promising early use case for quantum computing. There has been progress in the last five years from theoretical studies and numerical simulations to proof of concepts. Use cases demonstrated on contemporary quantum devices include classifying medical images and items from the Iris dataset, classifying and generating handwritten images, toxicity screening, and learning a probability distribution. Potential benefits of QML include faster training and identification of feature maps not found classically. Although, these examples lack the scale for commercial exploitation, and it may be several years before QML algorithms replace the classical solutions, QML is an exciting area. This article is written for those who already have a sound knowledge of quantum computing and now wish to gain a basic overview of the terminology and some applications of classical machine learning ready to study quantum machine learning. The reader will already understand the relevant relevant linear algebra, including Hilbert spaces, a vector space with an inner product., Comment: 32 pages, 21 figures, technical report

Brains have evolved a diverse set of neurons with varying morphologies, physiological properties and rich dynamics that impact their processing of temporal information. By contrast, most neural network models include a homogeneous set of units that only vary in terms of their spatial parameters (weights and biases). To investigate the importance of temporal parameters to neural function, we trained spiking neural networks on tasks of varying temporal complexity, with different subsets of parameters held constant. We find that in a tightly resource constrained setting, adapting conduction delays is essential to solve all test conditions, and indeed that it is possible to solve these tasks using only temporal parameters (delays and time constants) with weights held constant. In the most complex spatio-temporal task we studied, we found that an adaptable bursting parameter was essential. More generally, allowing for adaptation of both temporal and spatial parameters increases network robustness to noise, an important feature for both biological brains and neuromorphic computing systems. In summary, our findings highlight how rich and adaptable dynamics are key to solving temporally structured tasks at a low neural resource cost, which may be part of the reason why biological neurons vary so dramatically in their physiological properties., Comment: 14 pages, 6 figures

Behavioral sensing technologies are rapidly evolving across a range of well-being applications. Despite its potential, concerns about the responsible use of such technology are escalating. In response, recent research within the sensing technology has started to address these issues. While promising, they primarily focus on broad demographic categories and overlook more nuanced, context-specific identities. These approaches lack grounding within domain-specific harms that arise from deploying sensing technology in diverse social, environmental, and technological settings. Additionally, existing frameworks for evaluating harms are designed for a generic ML life cycle, and fail to adapt to the dynamic and longitudinal considerations for behavioral sensing technology. To address these gaps, we introduce a framework specifically designed for evaluating behavioral sensing technologies. This framework emphasizes a comprehensive understanding of context, particularly the situated identities of users and the deployment settings of the sensing technology. It also highlights the necessity for iterative harm mitigation and continuous maintenance to adapt to the evolving nature of technology and its use. We demonstrate the feasibility and generalizability of our framework through post-hoc evaluations on two real-world behavioral sensing studies conducted in different international contexts, involving varied population demographics and machine learning tasks. Our evaluations provide empirical evidence of both situated identity-based harm and more domain-specific harms, and discuss the trade-offs introduced by implementing bias mitigation techniques., Comment: 26 pages, 8 tables, and 1 figure (excluding appendix)

The use of synthetic data is recognized as a crucial step in the development of neural network-based Artificial Intelligence (AI) systems. While the methods for generating synthetic data for AI applications in other domains have a role in certain biomedical AI systems, primarily related to image processing, there is a critical gap in the generation of time series data for AI tasks where it is necessary to know how the system works. This is most pronounced in the ability to generate synthetic multi-dimensional molecular time series data (SMMTSD); this is the type of data that underpins research into biomarkers and mediator signatures for forecasting various diseases and is an essential component of the drug development pipeline. We argue the insufficiency of statistical and data-centric machine learning (ML) means of generating this type of synthetic data is due to a combination of factors: perpetual data sparsity due to the Curse of Dimensionality, the inapplicability of the Central Limit Theorem, and the limits imposed by the Causal Hierarchy Theorem. Alternatively, we present a rationale for using complex multi-scale mechanism-based simulation models, constructed and operated on to account for epistemic incompleteness and the need to provide maximal expansiveness in concordance with the Principle of Maximal Entropy. These procedures provide for the generation of SMMTD that minimizes the known shortcomings associated with neural network AI systems, namely overfitting and lack of generalizability. The generation of synthetic data that accounts for the identified factors of multi-dimensional time series data is an essential capability for the development of mediator-biomarker based AI forecasting systems, and therapeutic control development and optimization through systems like Drug Development Digital Twins., Comment: 16 pages, 2 Figures

It is important to develop sustainable processes in materials science and manufacturing that are environmentally friendly. AI can play a significant role in decision support here as evident from our earlier research leading to tools developed using our proposed machine learning based approaches. Such tools served the purpose of computational estimation and expert systems. This research addresses environmental sustainability in materials science via decision support in agile manufacturing using recycled and reclaimed materials. It is a safe and responsible way to turn a specific waste stream to value-added products. We propose to use data-driven methods in AI by applying machine learning models for predictive analysis to guide decision support in manufacturing. This includes harnessing artificial neural networks to study parameters affecting heat treatment of materials and impacts on their properties; deep learning via advances such as convolutional neural networks to explore grain size detection; and other classifiers such as Random Forests to analyze phrase fraction detection. Results with all these methods seem promising to embark on further work, e.g. ANN yields accuracy around 90\% for predicting micro-structure development as per quench tempering, a heat treatment process. Future work entails several challenges: investigating various computer vision models (VGG, ResNet etc.) to find optimal accuracy, efficiency and robustness adequate for sustainable processes; creating domain-specific tools using machine learning for decision support in agile manufacturing; and assessing impacts on sustainability with metrics incorporating the appropriate use of recycled materials as well as the effectiveness of developed products. Our work makes impacts on green technology for smart manufacturing, and is motivated by related work in the highly interesting realm of AI for materials science.

This is a study on the potential widespread usage of alternative fuel vehicles, linking them with the socio-economic status of the respective consumers as well as the impact on the resulting air quality index. Research in this area aims to leverage machine learning techniques in order to promote appropriate policies for the proliferation of alternative fuel vehicles such as electric vehicles with due justice to different population groups. Pearson correlation coefficient is deployed in the modeling the relationships between socio-economic data, air quality index and data on alternative fuel vehicles. Linear regression is used to conduct predictive modeling on air quality index as per the adoption of alternative fuel vehicles, based on socio-economic factors. This work exemplifies artificial intelligence for social good.

How will superhuman artificial intelligence (AI) affect human decision making? And what will be the mechanisms behind this effect? We address these questions in a domain where AI already exceeds human performance, analyzing more than 5.8 million move decisions made by professional Go players over the past 71 years (1950-2021). To address the first question, we use a superhuman AI program to estimate the quality of human decisions across time, generating 58 billion counterfactual game patterns and comparing the win rates of actual human decisions with those of counterfactual AI decisions. We find that humans began to make significantly better decisions following the advent of superhuman AI. We then examine human players' strategies across time and find that novel decisions (i.e., previously unobserved moves) occurred more frequently and became associated with higher decision quality after the advent of superhuman AI. Our findings suggest that the development of superhuman AI programs may have prompted human players to break away from traditional strategies and induced them to explore novel moves, which in turn may have improved their decision-making., Comment: This paper is published in PNAS: https://www.pnas.org/doi/10.1073/pnas.2214840120 Minor edits to v1 include the addition of watermark and link to the published paper in the footer

Two studies tested the hypothesis that a Large Language Model (LLM) can be used to model psychological change following exposure to influential input. The first study tested a generic mode of influence - the Illusory Truth Effect (ITE) - where earlier exposure to a statement (through, for example, rating its interest) boosts a later truthfulness test rating. Data was collected from 1000 human participants using an online experiment, and 1000 simulated participants using engineered prompts and LLM completion. 64 ratings per participant were collected, using all exposure-test combinations of the attributes: truth, interest, sentiment and importance. The results for human participants reconfirmed the ITE, and demonstrated an absence of effect for attributes other than truth, and when the same attribute is used for exposure and test. The same pattern of effects was found for LLM-simulated participants. The second study concerns a specific mode of influence - populist framing of news to increase its persuasion and political mobilization. Data from LLM-simulated participants was collected and compared to previously published data from a 15-country experiment on 7286 human participants. Several effects previously demonstrated from the human study were replicated by the simulated study, including effects that surprised the authors of the human study by contradicting their theoretical expectations (anti-immigrant framing of news decreases its persuasion and mobilization); but some significant relationships found in human data (modulation of the effectiveness of populist framing according to relative deprivation of the participant) were not present in the LLM data. Together the two studies support the view that LLMs have potential to act as models of the effect of influence., Comment: 24 pages, 6 figures, 7 tables, 53 references

The field of steganography has experienced a surge of interest due to the recent advancements in AI-powered techniques, particularly in the context of multimodal setups that enable the concealment of signals within signals of a different nature. The primary objectives of all steganographic methods are to achieve perceptual transparency, robustness, and large embedding capacity - which often present conflicting goals that classical methods have struggled to reconcile. This paper extends and enhances an existing image-in-audio deep steganography method by focusing on improving its robustness. The proposed enhancements include modifications to the loss function, utilization of the Short-Time Fourier Transform (STFT), introduction of redundancy in the encoding process for error correction, and buffering of additional information in the pixel subconvolution operation. The results demonstrate that our approach outperforms the existing method in terms of robustness and perceptual transparency., Comment: 8 pages, 5 figures, 2 tables

In creativity support and computational co-creativity contexts, the task of discovering appropriate prompts for use with text-to-image generative models remains difficult. In many cases the creator wishes to evoke a certain impression with the image, but the task of conferring that succinctly in a text prompt poses a challenge: affective language is nuanced, complex, and model-specific. In this work we introduce a method for generating images conditioned on desired affect, quantified using a psychometrically validated three-component approach, that can be combined with conditioning on text descriptions. We first train a neural network for estimating the affect content of text and images from semantic embeddings, and then demonstrate how this can be used to exert control over a variety of generative models. We show examples of how affect modifies the outputs, provide quantitative and qualitative analysis of its capabilities, and discuss possible extensions and use cases., Comment: 10 pages, 8 figures

Decision Trees are some of the most popular machine learning models today due to their out-of-the-box performance and interpretability. Often, Decision Trees models are constructed greedily in a top-down fashion via heuristic search criteria, such as Gini impurity or entropy. However, trees constructed in this manner are sensitive to minor fluctuations in training data and are prone to overfitting. In contrast, Bayesian approaches to tree construction formulate the selection process as a posterior inference problem; such approaches are more stable and provide greater theoretical guarantees. However, generating Bayesian Decision Trees usually requires sampling from complex, multimodal posterior distributions. Current Markov Chain Monte Carlo-based approaches for sampling Bayesian Decision Trees are prone to mode collapse and long mixing times, which makes them impractical. In this paper, we propose a new criterion for training Bayesian Decision Trees. Our criterion gives rise to BCART-PCFG, which can efficiently sample decision trees from a posterior distribution across trees given the data and find the maximum a posteriori (MAP) tree. Learning the posterior and training the sampler can be done in time that is polynomial in the dataset size. Once the posterior has been learned, trees can be sampled efficiently (linearly in the number of nodes). At the core of our method is a reduction of sampling the posterior to sampling a derivation from a probabilistic context-free grammar. We find that trees sampled via BCART-PCFG perform comparable to or better than greedily-constructed Decision Trees in classification accuracy on several datasets. Additionally, the trees sampled via BCART-PCFG are significantly smaller -- sometimes by as much as 20x., Comment: 10 pages, 1 figure

Under adversarial attacks, time series regression and classification are vulnerable. Adversarial defense, on the other hand, can make the models more resilient. It is important to evaluate how vulnerable different time series models are to attacks and how well they recover using defense. The sensitivity to various attacks and the robustness using the defense of several time series models are investigated in this study. Experiments are run on seven-time series models with three adversarial attacks and one adversarial defense. According to the findings, all models, particularly GRU and RNN, appear to be vulnerable. LSTM and GRU also have better defense recovery. FGSM exceeds the competitors in terms of attacks. PGD attacks are more difficult to recover from than other sorts of attacks., Comment: 8 pages, 3 figures, 7 tables

Propensity scores are commonly used to estimate treatment effects from observational data. We argue that the probabilistic output of a learned propensity score model should be calibrated -- i.e., a predictive treatment probability of 90% should correspond to 90% of individuals being assigned the treatment group -- and we propose simple recalibration techniques to ensure this property. We prove that calibration is a necessary condition for unbiased treatment effect estimation when using popular inverse propensity weighted and doubly robust estimators. We derive error bounds on causal effect estimates that directly relate to the quality of uncertainties provided by the probabilistic propensity score model and show that calibration strictly improves this error bound while also avoiding extreme propensity weights. We demonstrate improved causal effect estimation with calibrated propensity scores in several tasks including high-dimensional image covariates and genome-wide association studies (GWASs). Calibrated propensity scores improve the speed of GWAS analysis by more than two-fold by enabling the use of simpler models that are faster to train., Comment: 23 pages, 3 figures

Despite the rich existing literature about minimax optimization in continuous settings, only very partial results of this kind have been obtained for combinatorial settings. In this paper, we fill this gap by providing a characterization of submodular minimax optimization, the problem of finding a set (for either the min or the max player) that is effective against every possible response. We show when and under what conditions we can find such sets. We also demonstrate how minimax submodular optimization provides robust solutions for downstream machine learning applications such as (i) efficient prompt engineering for question answering, (ii) prompt engineering for dialog state tracking, (iii) identifying robust waiting locations for ride-sharing, (iv) ride-share difficulty kernelization, and (v) finding adversarial images. Our experiments demonstrate that our proposed algorithms consistently outperform other baselines.

In medical imaging, image synthesis is the estimation process of one image (sequence, modality) from another image (sequence, modality). Since images with different modalities provide diverse biomarkers and capture various features, multi-modality imaging is crucial in medicine. While multi-screening is expensive, costly, and time-consuming to report by radiologists, image synthesis methods are capable of artificially generating missing modalities. Deep learning models can automatically capture and extract the high dimensional features. Especially, generative adversarial network (GAN) as one of the most popular generative-based deep learning methods, uses convolutional networks as generators, and estimated images are discriminated as true or false based on a discriminator network. This review provides brain image synthesis via GANs. We summarized the recent developments of GANs for cross-modality brain image synthesis including CT to PET, CT to MRI, MRI to PET, and vice versa., Comment: 9 pages, 3 tabels, 4 figures

Despite remarkable successes, deep reinforcement learning algorithms remain sample inefficient: they require an enormous amount of trial and error to find good policies. Model-based algorithms promise sample efficiency by building an environment model that can be used for planning. Posterior Sampling for Reinforcement Learning is such a model-based algorithm that has attracted significant interest due to its performance in the tabular setting. This paper introduces Posterior Sampling for Deep Reinforcement Learning (PSDRL), the first truly scalable approximation of Posterior Sampling for Reinforcement Learning that retains its model-based essence. PSDRL combines efficient uncertainty quantification over latent state space models with a specially tailored continual planning algorithm based on value-function approximation. Extensive experiments on the Atari benchmark show that PSDRL significantly outperforms previous state-of-the-art attempts at scaling up posterior sampling while being competitive with a state-of-the-art (model-based) reinforcement learning method, both in sample efficiency and computational efficiency.

Unsupervised anomaly detection (AD) is critical for a wide range of practical applications, from network security to health and medical tools. Due to the diversity of problems, no single algorithm has been found to be superior for all AD tasks. Choosing an algorithm, otherwise known as the Algorithm Selection Problem (ASP), has been extensively examined in supervised classification problems, through the use of meta-learning and AutoML, however, it has received little attention in unsupervised AD tasks. This research proposes a new meta-learning approach that identifies an appropriate unsupervised AD algorithm given a set of meta-features generated from the unlabelled input dataset. The performance of the proposed meta-learner is superior to the current state of the art solution. In addition, a mixed model statistical analysis has been conducted to examine the impact of the meta-learner components: the meta-model, meta-features, and the base set of AD algorithms, on the overall performance of the meta-learner. The analysis was conducted using more than 10,000 datasets, which is significantly larger than previous studies. Results indicate that a relatively small number of meta-features can be used to identify an appropriate AD algorithm, but the choice of a meta-model in the meta-learner has a considerable impact., Comment: 16 pages, 4 figures

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness, explainability, and transparency. However, there are potential tensions between these aspects that pose difficulties for AI/ML developers seeking to follow these principles. For example, increasing the accuracy of an AI/ML system may reduce its explainability. As part of the ongoing effort to operationalise the principles into practice, in this work we compile and discuss a catalogue of 10 notable tensions, trade-offs and other interactions between the underlying aspects. We primarily focus on two-sided interactions, drawing on support spread across a diverse literature. This catalogue can be helpful in raising awareness of the possible interactions between aspects of ethics principles, as well as facilitating well-supported judgements by the designers and developers of AI/ML systems.

Structural health monitoring (SHM) tasks like damage detection are crucial for decision-making regarding maintenance and deterioration. For example, crack detection in SHM is crucial for bridge maintenance as crack progression can lead to structural instability. However, most AI/ML models in the literature have low latency and late inference time issues while performing in real-time environments. This study aims to explore the integration of edge-AI in the SHM domain for real-time bridge inspections. Based on edge-AI literature, its capabilities will be valuable integration for a real-time decision support system in SHM tasks such that real-time inferences can be performed on physical sites. This study will utilize commercial edge-AI platforms, such as Google Coral Dev Board or Kneron KL520, to develop and analyze the effectiveness of edge-AI devices. Thus, this study proposes an edge AI framework for the structural health monitoring domain. An edge-AI-compatible deep learning model is developed to validate the framework to perform real-time crack classification. The effectiveness of this model will be evaluated based on its accuracy, the confusion matrix generated, and the inference time observed in a real-time setting., Comment: 7 pages, 8 figures

The growth of market capitalisation and the number of altcoins (cryptocurrencies other than Bitcoin) provide investment opportunities and complicate the prediction of their price movements. A significant challenge in this volatile and relatively immature market is the problem of predicting cryptocurrency prices which needs to identify the factors influencing these prices. The focus of this study is to investigate the factors influencing altcoin prices, and these factors have been investigated from a causal analysis perspective using Bayesian networks. In particular, studying the nature of interactions between five leading altcoins, traditional financial assets including gold, oil, and S\&P 500, and social media is the research question. To provide an answer to the question, we create causal networks which are built from the historic price data of five traditional financial assets, social media data, and price data of altcoins. The ensuing networks are used for causal reasoning and diagnosis, and the results indicate that social media (in particular Twitter data in this study) is the most significant influencing factor of the prices of altcoins. Furthermore, it is not possible to generalise the coins' reactions against the changes in the factors. Consequently, the coins need to be studied separately for a particular price movement investigation.

Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR., Comment: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

The use of artificial intelligence (AI) in research across all disciplines is becoming ubiquitous. However, this ubiquity is largely driven by hyperspecific AI models developed during scientific studies for accomplishing a well-defined, data-dense task. These AI models introduce apparent, human-recognizable biases because they are trained with finite, specific data sets and parameters. However, the efficacy of using large language models (LLMs) -- and LLM-powered generative AI tools, such as ChatGPT -- to assist the research process is currently indeterminate. These generative AI tools, trained on general and imperceptibly large datasets along with human feedback, present challenges in identifying and addressing biases. Furthermore, these models are susceptible to goal misgeneralization, hallucinations, and adversarial attacks such as red teaming prompts -- which can be unintentionally performed by human researchers, resulting in harmful outputs. These outputs are reinforced in research -- where an increasing number of individuals have begun to use generative AI to compose manuscripts. Efforts into AI interpretability lag behind development, and the implicit variations that occur when prompting and providing context to a chatbot introduce uncertainty and irreproducibility. We thereby find that incorporating generative AI in the process of writing research manuscripts introduces a new type of context-induced algorithmic bias and has unintended side effects that are largely detrimental to academia, knowledge production, and communicating research., Comment: 10 pages, 6 figures

Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have matured significantly, mainly thanks to the use of Neural Networks (NNs) as a predictor. While their performance is difficult to beat in the general case, there are specific situations where background process knowledge can be helpful. Such knowledge can be leveraged for improving the quality of predictions for exceptional process executions or when the process changes due to a concept drift. In this paper, we present a Symbolic[Neuro] system that leverages background knowledge expressed in terms of a procedural process model to offset the under-sampling in the training data. More specifically, we make predictions using NNs with attention mechanism, an emerging technology in the NN field. The system has been tested on several real-life logs showing an improvement in the performance of the prediction task.

This paper considers learning the hidden causal network of a linear networked dynamical system (NDS) from the time series data at some of its nodes -- partial observability. The dynamics of the NDS are driven by colored noise that generates spurious associations across pairs of nodes, rendering the problem much harder. To address the challenge of noise correlation and partial observability, we assign to each pair of nodes a feature vector computed from the time series data of observed nodes. The feature embedding is engineered to yield structural consistency: there exists an affine hyperplane that consistently partitions the set of features, separating the feature vectors corresponding to connected pairs of nodes from those corresponding to disconnected pairs. The causal inference problem is thus addressed via clustering the designed features. We demonstrate with simple baseline supervised methods the competitive performance of the proposed causal inference mechanism under broad connectivity regimes and noise correlation levels, including a real world network. Further, we devise novel technical guarantees of structural consistency for linear NDS under the considered regime., Comment: Accepted at The 38th AAAI Conference on Artificial Intelligence (Main Track). Final Camera-Ready Version

Biometry has proved its capability in terms of recognition accuracy. Now, it is widely used for automated border control with the biometric passport, to unlock a smartphone or a computer with a fingerprint or a face recognition algorithm. While identity verification is widely democratized, pure identification with no additional clues is still a work in progress. The identification difficulty depends on the population size, as the larger the group is, the larger the confusion risk. For collision prevention, biometric traits must be sufficiently distinguishable to scale to considerable groups, and algorithms should be able to capture their differences accurately. Most biometric works are purely experimental, and it is impossible to extrapolate the results to a smaller or a larger group. In this work, we propose a theoretical analysis of the distinguishability problem, which governs the error rates of biometric systems. We demonstrate simple relationships between the population size and the number of independent bits necessary to prevent collision in the presence of noise. This work provides the lowest lower bound for memory requirements. The results are very encouraging, as the biometry of the whole Earth population can fit in a regular disk, leaving some space for noise and redundancy., Comment: 19 pages

Hydropower plants are crucial for stable renewable energy and serve as vital water sources for sustainable agriculture. However, it is essential to assess the current water management practices associated with hydropower plant management software. A key concern is the potential conflict between electricity generation and agricultural water needs. Prioritising water for electricity generation can reduce irrigation availability in agriculture during crucial periods like droughts, impacting crop yields and regional food security. Coordination between electricity and agricultural water allocation is necessary to ensure optimal and environmentally sound practices. Neural networks have become valuable tools for hydropower plant management, but their black-box nature raises concerns about transparency in decision making. Additionally, current approaches often do not take advantage of their potential to create a system that effectively balances water allocation. This work is a call for attention and highlights the potential risks of deploying neural network-based hydropower plant management software without proper scrutiny and control. To address these concerns, we propose the adoption of the Agriculture Conscious Hydropower Plant Management framework, aiming to maximise electricity production while prioritising stable irrigation for agriculture. We also advocate reevaluating government-imposed minimum water guidelines for irrigation to ensure flexibility and effective water allocation. Additionally, we suggest a set of regulatory measures to promote model transparency and robustness, certifying software that makes conscious and intelligent water allocation decisions, ultimately safeguarding agriculture from undue strain during droughts.

This paper reviews the challenges hindering the widespread adoption of artificial intelligence (AI) solutions in the healthcare industry, focusing on computer vision applications for medical imaging, and how interoperability and enterprise-grade scalability can be used to address these challenges. The complex nature of healthcare workflows, intricacies in managing large and secure medical imaging data, and the absence of standardized frameworks for AI development pose significant barriers and require a new paradigm to address them. The role of interoperability is examined in this paper as a crucial factor in connecting disparate applications within healthcare workflows. Standards such as DICOM, Health Level 7 (HL7), and Integrating the Healthcare Enterprise (IHE) are highlighted as foundational for common imaging workflows. A specific focus is placed on the role of DICOM gateways, with Smart Routing Rules and Workflow Management leading transformational efforts in this area. To drive enterprise scalability, new tools are needed. Project MONAI, established in 2019, is introduced as an initiative aiming to redefine the development of medical AI applications. The MONAI Deploy App SDK, a component of Project MONAI, is identified as a key tool in simplifying the packaging and deployment process, enabling repeatable, scalable, and standardized deployment patterns for AI applications. The abstract underscores the potential impact of successful AI adoption in healthcare, offering physicians both life-saving and time-saving insights and driving efficiencies in radiology department workflows. The collaborative efforts between academia and industry, are emphasized as essential for advancing the adoption of healthcare AI solutions., Comment: 13 pages, 6 figures

Among ensemble clustering methods, Evidence Accumulation Clustering is one of the simplest technics. In this approach, a co-association (CA) matrix representing the co-clustering frequency is built and then clustered to extract consensus clusters. Compared to other approaches, this one is simple as there is no need to find matches between clusters obtained from two different partitionings. Nevertheless, this method suffers from computational issues, as it requires to compute and store a matrix of size n x n, where n is the number of items. Due to the quadratic cost, this approach is reserved for small datasets. This work describes a trick which mimic the behavior of average linkage clustering. We found a way of computing efficiently the density of a partitioning, reducing the cost from a quadratic to linear complexity. Additionally, we proved that the k-means maximizes naturally the density. We performed experiments on several benchmark datasets where we compared the k-means and the bisecting version to other state-of-the-art consensus algorithms. The k-means results are comparable to the best state of the art in terms of NMI while keeping the computational cost low. Additionally, the k-means led to the best results in terms of density. These results provide evidence that consensus clustering can be solved with simple algorithms., Comment: 18 pages, proofread not completed