Search

Digital technologies sustain today's world. Every part of the world is working towards digital technologies, which none of us can eliminate. Enormous growth is achieved only by unexpected acceleration by digital technologies, including the Internet of Everything (IoE), Artificial Neural Networks (ANN), Machine Learning (ML), Internet of Things (IoT), Artificial Intelligence (AI), Deep Learning (DL), and many more. These technologies started occupying all the engineering sectors, including manufacturing. This paper focuses on tribology analysis related to manufacturing concerning various digital manufacturing technologies. The paper narration includes Tribology using digital technologies wherein the journals and patent landscape analysis abet them. In trend, Tribology utilizes all these technologies today and envisages its growth with the predominant technological invention in the border view. The survey of various literature reveals that only three digital technologies, including AI, ML, and ANN, are used by tribologists around the globe. Other Technologies like Evolutionary Algorithm (EA), Support Vector Machine (SVM), and Adaptive Neuro-Fuzzy Interference Systems (ANFIS) are not used predominantly. [ABSTRACT FROM AUTHOR]

This document serves as a preface to a special issue of the International Journal on Artificial Intelligence Tools (IJAIT). The articles in this issue build upon papers presented at the 36th International Florida AI Research Society Conferences in May 2023. The lead article introduces the theme of the special issue, which is explainable, fair, and Trustworthy AI. Other articles in the issue cover topics such as improving the bounds of a neuron's Boolean function, ethical explanations and transparency in AI systems, fairness measurement and mitigation in deep learning systems, and the dynamics of human-agent collaboration in ad hoc teams. The paper emphasizes the importance of positive and negative contrastive explanations in enhancing motivation and performance. It also addresses the challenges of fairness and reliability in predictive policing systems, with a focus on reducing bias related to race, age, and sex. The authors propose tailoring predictive models to specific causal queries and utilizing causal structure instead of relying solely on pre-trained models. The paper also explores how machine learning models can balance accuracy and understandability, as well as ensure fairness. The findings indicate that more complex models tend to outperform current guidelines, but fair models have lower complexity. The paper concludes by expressing gratitude to the reviewers for their contributions and support. [Extracted from the article]

Monitoring and managing litter on the roadways is important not only for preserving the cleanliness and esthetic appeal of our cities but also for safeguarding the overall health and sanitary environment of citizens. With the development of artificial intelligence, it is now possible to design algorithms capable of autonomously assessing the sanitation status of roadways. In this paper, we propose a method for detecting garbage on roads as our solution to tackle the issue. The proposed model is a deep learning model with an attention mechanism introduced to detect garbage in real-time scenarios. Furthermore, the object recognition capability of the model is enhanced through transfer learning to mitigate the influence of irrelevant content during training. The refined network can detect rubbish on roads with higher efficiency than the existing models. Also, compared with other methods, it consumes less amount of data for training. The experimental results demonstrate the efficiency of our proposed model, with a performance boost of 7.62% over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

A variant of membrane computing models called Spiking Neural P systems (SNP systems) closely mimics the structure and behavior of biological neurons. As third-generation neural networks, SNP systems have flexible architectures allowing the design of bio-inspired machine learning algorithms. This paper proposes Modular Spiking Neural P (MSNP) systems to solve image classification problems, a novel SNP system to be applied in scenarios where hundreds or even thousands of different classes are considered. A main issue to face in such situations is related to the structural complexity of the network. MSNP systems devised in this work allow to approach the general classification problem by dividing it in smaller parts, that are then faced by single entities of the network. As a benchmark dataset, the Oxford Flowers 102 dataset is considered, consisting of more than 8000 pictures of flowers belonging to the 102 species commonly found in the UK. These classes sometimes present large variations within them, may be also very similar to one another, and different images of the same subject may differ a lot. The work describes the architecture of the MSNP system, based on modules focusing on a specific class, their training phase, and the evaluation of the model both concerning result accuracy as well as energy consumption. Experimental results on image classification problems show that the model achieves good results, but is strongly connected to image quality, mainly depending on the frequency of images, remarkable changes of pose, images not centered, and subject mostly not shown. [ABSTRACT FROM AUTHOR]

Keeping in view the design of short to medium-span bridges in critical locations such as road/river crossings under the action of oppositely moving high-speed loads, this paper presents a hybrid model for the prediction of dynamic displacement employing a theoretical non-dimensional framework aided by an artificial neural network (ANN). The introduction of such a hybrid model reduces parametric space and time. The feed-forward ANN is implemented to train the comprehensive data set obtained from the non-dimensional theoretical scheme. The dimensionless input to ANN comprises the bridge and load parameters, whereas maximum dynamic displacement is the output parameter. The robustness and efficiency of the proposed surrogate ANN framework in terms of computational efficiency are compared with the conventional mode-superposition method formulated in dimensionless form. The training of test and validated data sets results in best-fit models with optimistic statistical metrics and accuracy ≤ 6%. Moreover, the sensitivity of different parameters to the displacement response is highlighted using Pearson's correlation and Quantile–Quantile plots. To incorporate the best-fit models into the design by bypassing the high-fidelity model, a user-friendly interface is developed, confirming the standards of the high-speed rating code (TZY2014-232 2014). Such interfaces have the potential for wide application in the preliminary design of short-to medium-span bridges under opposite moving loads in critical locations such as crossing valleys, rivers, and railroads. [ABSTRACT FROM AUTHOR]

The price of carbon emission rights in the market fluctuates greatly due to various factors from economy, finance, and climate. For an enterprise that needs to conduct carbon trading activities, it is extremely necessary to fully grasp the price of carbon trading in the future period. Thus in this paper, a deep neural network-based assistive decision model for financial risk prediction in carbon trading market is proposed for this purpose. Specifically, the dynamic risk spillover effects of domestic and international carbon trading markets are studied, and a frontier time-varying model is utilized to measure the risk spillover effects. Then, the deep neural network is used for quantitative research and to construct an intelligent decision scheme that outputs financial risk prediction results. Four perspectives, energy price, climate environment, carbon market price, and macroeconomics, are selected as the input to analyze the influence factors of carbon emission rights price. Finally, several linear regression models are adopted as the baseline methods for comparison, and experimental results show that the proposed method can achieve better prediction performance compared with baseline methods. [ABSTRACT FROM AUTHOR]

Several hardware Trojan (HT) detection techniques are available today to ensure the security of hardware systems. However, the existing pre-silicon HT detection techniques have problems such as difficulties in capturing HT path features and poor applicability. To address these challenges, this paper proposes a gate-level HT detection scheme based on a deep learning model. We parse the circuit gate-level netlist and develop an algorithm to extract circuit path sentences based on the signal propagation rule. Path sentences consisting of gate names are extracted as experimental datasets. We apply the theory of natural language processing (NLP) to the task of HT detection and use three neural networks to filter the length of path sentences. Then, based on the deep learning model text convolutional neural network (TextCNN), we propose PS-TextCNN for HT detection. Our approach is verified on seven benchmark circuits of the RS232-series and eight benchmark circuits of the s-series. We achieve an average true positive rate (TPR) of 88.9%. The TPR of the RS232-series reaches a high score of 99.5%. The TPR of the s-series is 79.5%, which is significantly higher than that of the existing gate-level HT detection techniques. [ABSTRACT FROM AUTHOR]

The credit risk assessment acts as an important part in daily affairs for financial institutions. But in the era of big data, the growing business volume makes it an urgent demand to develop digital ways of credit risk assessment. Currently, the machine learning is universally employed to establish various data-driven models for this purpose. However, machine learning models generally suffer from limited ability of feature representation and robustness, and cannot deal with more complex financial security scenarios. To deal with this issue, this work introduces ensemble learning to construct a stronger credit risk prediction model via integration of several basic machine learning models. Thus, an ensemble learning-enhanced smart prediction model for financial credit risk is proposed in this paper. Three classification-based machine learning models (support vector machine, artificial neural network and radial basis function) are selected as the basic classifiers, and "voting" strategy is utilized to integrate them into a novel strong classifier. A real-world financial credit dataset released by a Chinese commercial bank was selected as the experimental scenario. The obtained results show that the proposal has better prediction accuracy compared with basic machine learning models without ensemble learning. [ABSTRACT FROM AUTHOR]

Deep neural network has made surprising achievements in natural language processing, image pattern classification recognition, and other domains in the last few years. It is still tough to apply to hardware-constrained or mobile equipment because of the huge number of parameters, high storage as well as computing costs. In this paper, a new sparse iteration neural network architecture is proposed. First, the pruning method is used to compress the model size and make the network sparse. Then the architecture is iterated on the sparse network model, and the network performance is improved without adding additional parameters. Finally, the hybrid deep learning model was carried out on CV tasks and NLP tasks on ANN, CNN, and Transformer. Compared with the sparse network architecture, we finally found that the accuracy of the MINST, CIFAR10, PASCAL VOC 2012, and SQuAD datasets is improved by 0.47%, 0.64%, 3.75%, and 15.06%, respectively. [ABSTRACT FROM AUTHOR]

This paper presents a novel discrete memristor model that incorporates exponential and absolute value functions. A discrete coupled memristor neural network model is constructed based on this memristor design. The periodic and chaotic regions of the discrete neural network model are determined using bifurcation and Lyapunov exponent spectrum. Furthermore, by varying the initial values of the discrete memristive neural network, we observe the coexistence of chaos and periodic attractors, as well as periodic attractors. Additionally, an application to color image encryption based on the discrete system model is given. Security analysis is conducted in the aspects of key space, histogram analysis, correlation analysis, sensitivity analysis, Peak Signal-to-Noise Ratio (PSNR), and information entropy analysis. The analysis results show that the algorithm has a key space size of 2 2 5 8 , and the information entropy of baboon graph is 7.9993, which is very close to the ideal value of 8. It shows that the image encryption algorithm is feasible and effective. Finally, the implementation of the discrete memristive neural network model is realized using Field Programmable Gate Array (FPGA). The experimental implementation is conducted using the Verilog language on the Vivado 2018.3 platform, and the obtained results align with the numerical simulation results obtained through MATLAB. [ABSTRACT FROM AUTHOR]

The Π -shaped open section girder is a very common section, which has been widely used in the construction of modern bridges. However, compared with a streamlined box girder, it is easy to cause vortex-induced vibration (VIV) in bridges due to its bluff section shape and poor aerodynamic stability. In this paper, a typical open section with a height–width ratio of 10:1 is taken as the research object. Through wind tunnel tests and numerical simulation technology, the time-history data of VIV of the Π -shaped section are obtained. By selecting three different neural network models to establish the relationship between external parameters (wind attack angle, wind speed, turbulence) and structural response parameters (the onset wind speed of VIV, the length of the lock-in interval). After comparing different machine learning methods, the most suitable machine learning model is selected to predict the VIV response characteristics of the main girder. The research results show that the typical open section has a serious VIV phenomenon. The BP neural network model has the best performance in predicting the VIV performance of the open section in terms of calculation speed, prediction accuracy and solving nonlinear adaptability. At the same time, it is found that different characteristic parameters of the incoming wind field have different influences on the prediction results of the VIV response. Among them, the wind attack angle is the key parameter that affects the onset wind speed of VIV, but the turbulence intensity has a greater impact on the maximum amplitude of VIV. At the same time, the optimized BP model can predict the characteristic parameters of VIV response under unknown wind fields. This paper provides a new idea to study the effect of different incoming flow parameters on the performance of section VIV and further improves people's understanding of VIV system. [ABSTRACT FROM AUTHOR]

This paper proposes a methodology for the diagnosis of electrical system conditions using fractional-order integral transforms for feature extraction. This work proposes three feature extraction algorithms using the Fractional Fourier Transform (FRFT), the Fourier Transform combined with the Mittag-Leffler function, and the Wavelet Transform (WT). Each algorithm extracts data from an electrical system to obtain a set of features that are classified by an Artificial Neural Network to determine the system's condition. The algorithms are utilized in diagnosing two types of electrical machine faults, one in a photovoltaic system, and another in classifying the power quality disturbances (PQDs). An optimization algorithm is suggested to find the optimal orders of integral transforms. The obtained results demonstrate the system's effective diagnosis, displaying superior performance in classifying the faults and PQDs with complex signals. [ABSTRACT FROM AUTHOR]

Deep learning based on deep neural networks has been very successful in many practical applications, but it lacks enough theoretical understanding due to the network architectures and structures. In this paper, we establish some analysis for linear feature extraction by a deep multi-channel convolutional neural networks (CNNs), which demonstrates the power of deep learning over traditional linear transformations, like Fourier, wavelets, redundant dictionary coding methods. Moreover, we give an exact construction presenting how linear features extraction can be conducted efficiently with multi-channel CNNs. It can be applied to lower the essential dimension for approximating a high-dimensional function. Rates of function approximation by such deep networks implemented with channels and followed by fully connected layers are investigated as well. Harmonic analysis for factorizing linear features into multi-resolution convolutions plays an essential role in our work. Nevertheless, a dedicate vectorization of matrices is constructed, which bridges 1D CNN and 2D CNN and allows us to have corresponding 2D analysis. [ABSTRACT FROM AUTHOR]

In recent years, deep learning has revolutionized natural language processing (NLP) by enabling the development of models that can learn complex representations of language data, leading to significant improvements in performance across a wide range of NLP tasks. Deep learning models for NLP typically use large amounts of data to train deep neural networks, allowing them to learn the patterns and relationships in language data. This is in contrast to traditional NLP approaches, which rely on hand-engineered features and rules to perform NLP tasks. The ability of deep neural networks to learn hierarchical representations of language data, handle variable-length input sequences, and perform well on large datasets makes them well-suited for NLP applications. Driven by the exponential growth of textual data and the increasing demand for condensed, coherent, and informative summaries, text summarization has been a critical research area in the field of NLP. Applying deep learning to text summarization refers to the use of deep neural networks to perform text summarization tasks. In this survey, we begin with a review of fashionable text summarization tasks in recent years, including extractive, abstractive, multi-document, and so on. Next, we discuss most deep learning-based models and their experimental results on these tasks. The paper also covers datasets and data representation for summarization tasks. Finally, we delve into the opportunities and challenges associated with summarization tasks and their corresponding methodologies, aiming to inspire future research efforts to advance the field further. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific setting. This survey aims to provide a comprehensive review of existing techniques, evaluation methodologies, and practical applications of automatic text summarization. [ABSTRACT FROM AUTHOR]

Prediction of the stock market can play a vital role in everyone's life to attain sustainable growth. This can also lead to an attractive profit by making the proper choices in the financial stock market. The stock market prediction is a big challenge which requires extensive advanced tools and techniques to analyze the future and present data. The modern stock market institutions provide better self-trading and investment options, enabling regular people and traders to enter the market through numerous online applications and websites that are available via smart devices. Financial institutions are investing more and more in talent development so that investors may make the maximum money. There are a multitude of reasons for this, including volatility of market and a collection of other interrelated and independent parameters that control the market value of a different stock. Because of these factors, it is excessively difficult for any specialist in financial markets to accurately predict the market's rise and collapse. This research paper proposed an artificial neural network (ANN) technique which combines with fuzzy logic to predict the stock market for short duration with high accuracy. First, historical and real-time data are used to classify and gather information for prediction. Then the short-duration prediction is done with a high accuracy of 96% and the error margin for a small instance is 2.3%. Through training, testing and validation it is clear that for sustainable short duration prediction, ANN integrated with fuzzy is a good choice. [ABSTRACT FROM AUTHOR]

This document is a guest editorial for a special issue of the journal "Fluctuation & Noise Letters" on the topic of economic policy uncertainty and the energy stock market. The editorial highlights the importance of stable economic policies for consistent economic growth and discusses the negative correlation between economic policy uncertainty and the energy stock market. It also explores the integration of machine learning and artificial intelligence in finance and their potential to reduce economic policy uncertainty. The special issue includes 14 peer-reviewed papers that cover various aspects of energy economics, energy materials, energy stock market prediction, green energy commercialization, and renewable energy dynamics in society. [Extracted from the article]

Deep Neural Networks (DNNs) have been successfully applied to investigations of numerical dynamics of finite-dimensional nonlinear systems such as ODEs instead of finding numerical solutions to ODEs via the traditional Runge–Kutta method and its variants. To show the advantages of DNNs, in this paper, we demonstrate that the DNNs are more efficient in finding topological horseshoes in chaotic dynamical systems. [ABSTRACT FROM AUTHOR]

To improve the recognition ability of clinical named entity recognition (CNER) in a limited number of Chinese electronic medical records, it provides meaningful support for clinical advanced knowledge extraction. In this paper, using CCKS2019 Chinese electronic medical record as an experimental data source, a fusion model enhanced by knowledge graph (KG) is proposed, and the model is applied to specific Chinese CNER tasks. This study consists of three main parts: single-mode model construction and comparison experiment, KG enhancement experiment, and model fusion experiment. The model has achieved good performance in CNER from the results. The accuracy rate, recall rate, and F1 value are 83.825%, 84.705%, and 84.263%, respectively, which is the global optimal, which proves the effectiveness of the model. This provides a good help for further research of medical information. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Variable selection is one of the most important contents of machine learning research and a large number of variable selection methods have been proposed at present. From deep learning perspective, we propose a new variable selection method based on multi-layer artificial neural networks in this paper. The method propagates errors gained form a trained network model through the network from output layer to input layer and the values gained by input layer give information about the relative contribution. The variables with big contribution value are selected, which we call neural inverse propagation (NIP). Specifically, after training a neural network, the gained errors between the actual network outputs and the desired outputs go through the network from top to down and arrive at the input layer. The absolute values gained by input units provide information about the relative importance (contribution) of input units, which is that the larger the value is, the more important the corresponding input variable is. We remove k variables corresponding to the first k minimum absolute value gained by input units to the predictive variables, to perform variable selection. The efficiency of the proposed method is illustrated through its application to classification and regression tasks on a number of synthetic datasets and a real-world image classification dataset. [ABSTRACT FROM AUTHOR]

The article discusses the use of model predictive control (MPC) for drone flight control in unknown dynamic environments. MPC is a practical method for drone flight control due to its robustness against modeling errors and uncertainties. However, it can degrade in performance when faced with unknown environmental dynamics. The paper introduces a parameterized MPC approach called hyMPC that adapts to uncertain environmental conditions. It uses a novel policy search framework to train a high-level Gaussian policy and neural network policies to provide real-time decision variables. The effectiveness of hyMPC is validated through numerical simulations, achieving a 100% success rate in drone flight tests. The text discusses a framework for maneuvering drones through swinging gates using reinforcement learning (RL) and model predictive control (MPC). The framework utilizes episode-based policy search methods to acquire parameterized motor primitives and skills for controlling the drone. The RL-driven MPC framework incorporates a multi-layer perceptron to predict the gate's future state and a hybrid MPC cost function for trajectory optimization. The policy parameters are updated using a reward function that evaluates the quality of sampled trajectories. The proposed framework is validated through numerical simulations. This document presents a novel framework for navigating drones through swinging gates with unknown dynamics. The framework combines real-time Model Predictive Control (MPC) and offline Reinforcement Learning (RL) techniques. The approach involves training a neural network to predict gate motions and using an MLP to guide trajectory planning. The framework divides the traversal task into gate-following and gate-traversing [Extracted from the article]

Electric Vehicles (EVs) are powered by a battery mounted in the vehicle, which powers the motor and drives the wheels. Most commercial EVs can be charged by plugging them into a charging station. Such conductive recharging has various drawbacks, including physical plugging of the cable, safety concerns, and charging time. Manually charging EVs might be dangerous due to the chance of an electric spark or disaster. Advances in Wireless Power Transfer (WPT) demonstrate the capacity to transfer significant amounts of electricity over short and medium-range distances. The ultimate purpose of this paper is to improve the efficacy of electric car wireless charging systems. Here, a hybrid optimization-based Artificial Neural Network (ANN) model is applied to improve the efficacy of the WPT model in EVs. To optimize the weights of the ANN classifier, a hybrid approach termed as Grasshopper-Assisted Elephant Herd Optimization (GA-EHO) method is proposed. The GA-EHO is derived through the hybridization of Elephant Herd Optimization (EHO) Algorithm and the Grasshopper Optimization Algorithm (GOA) techniques. Finally, the experimental study reveals that at 70% learning rate, the proposed ANN system achieves a minimal MSE value of 0.0528, which is lower than other current classifiers, such as SVM, LSTM, and CNN. [ABSTRACT FROM AUTHOR]

The vibration-based identification method has long been used as an alternative to mechanical tests for material characterization. Its non-destructive nature, high efficiency in parameter identification of anisotropic materials and its ability to achieve structure-level homogenization make it very attractive for both academic community and industry. Due to the absence of explicit mapping from the result of vibration test to elastic constants, conventional vibration-based identification approaches generally rely on the minimization of a cost function built on modal properties or Frequency Response Function (FRF) curve. In this paper, a direct relation from FRFs to mechanical properties is established by deep neural network, which offers a new perspective to solve the inverse identification problem. Specifically, this mapping is approximately built with Multilayer Perceptrons (MLPs) and the network's weights are learned from massive training data. The training data-i.e., the FRF curves, is generated by a finite element model whose input parameters are selected by Latin Hypercube Sampling (LHS). After training, the obtained model is validated by dataset unseen during training process and will be further used to predict mechanical properties of materials from FRFs obtained by vibration test. The effectiveness and efficiency of the developed method are demonstrated on the case study of an aluminum plate. Both the Young's modulus and Poisson's ratio are retrieved with high accuracy. [ABSTRACT FROM AUTHOR]

The recognition of steel microstructure images plays a crucial role in the metallographic analysis process. Although some progress has been made through the application of artificial intelligence algorithms, several challenges remain. First, existing algorithms exhibit weak nonlinear feature extraction capabilities and noticeable limitations. Second, they overlook the intrinsic noise and redundant interference present in microscopic images. To address these issues, this paper investigates the automatic recognition of metallographic tissues by leveraging residual structures in deep neural networks. An enhanced residual network model based on transfer learning is proposed, which utilizes the pre-trained weights from the ImageNet dataset to facilitate learning with small sample data. This network offers higher classification accuracy and higher F1 scores. In addition, a deep residual shrinkage network model based on an attention mechanism is proposed. This model incorporates an attention sub-network into the original residual module and employs a soft threshold function to eliminate redundant features, including noise. The proposed algorithms are evaluated against various convolutional neural networks using 20 types of metallographic test sets. The experimental results showed that both methods have high accuracy rates of 95% and 94.44%, respectively, and F1 scores of 0.9464 and 0.9419. While maintaining the complexity of the model, there has been a significant improvement in accuracy, and the models exhibit strong generalization capabilities. Our research contributes to enhancing production efficiency, strengthening quality control, and improving material performance through computer vision technology. [ABSTRACT FROM AUTHOR]

Recent advances in speaker embeddings promote a great development of speaker diarization. However, determining 'who spoke when' in the meeting scenarios is still challenging due to similar speaker voices and unknown speaker quantity. In this paper, this research proposes enhanced discriminative features for speaker diarization, including discriminative speaker-specific features based on Siamese networks, and a speaker re-verification method. With Siamese architecture, SiamTDNN, this research first explores latent representations which is capable of modeling intra-class and inter-class differences between speakers, by training with audio pairs. Then, the re-verification method is introduced with a local-global strategy to identify speakers in a multi-person talking scene. Our method provides a novel speaker embedding with enhanced discriminative power for disambiguated speakers and achieves an elevated upper bound on the number of speakers. The proposed speaker embedding achieved an EER of 1.1% and a minDCF of 0.1192 on VoxCeleb1 for the speaker verification task. Extensive experiments on AiShell-4, ICSI, AMI and VoxConverse demonstrate the effectiveness of the proposed method with an average DER reduction of 3% and an RTF of 0.0792. [ABSTRACT FROM AUTHOR]

This paper aims to propose an improved image classification model to reduce the cost of model construction. Aiming at the problem that network training usually requires the support of a large number of labeled samples, an image classification model based on semi-supervised deep learning is proposed, which uses labeled samples to guide the network to learn unlabeled samples. A convolutional neural network model for simultaneous processing of labeled and unlabeled data is constructed. The tagged data is used to train the Softmax classifier and provide the initial K-means clustering center for the untagged data. The nonsubsampling contourlet layer is used to replace the first convolutional layer of the full convolutional neural network to extract multi-scale depth features, and the nonsubsampling contourlet full convolutional neural network is constructed. The network can extract multi-scale information of the images to be classified, and extract more discriminative deep image features. In addition, the parameters of the nonsubsampled contourlet layers are pre-set and do not require network training. The proposed method has higher classification accuracy than the contrast method on polarimetric SAR images using the nonsubsampled contourlet full convolutional neural network. [ABSTRACT FROM AUTHOR]

Using deep neural networks to solve partial differential equations (PDEs) has attracted a lot of attention recently. However, why the deep learning method works is falling far behind its empirical success. In this paper, we provide a rigorous numerical analysis on the deep Ritz method (DRM) for second-order elliptic equations with Dirichlet, Neumann and Robin boundary conditions, respectively. We establish the first nonasymptotic convergence rate in H 1 norm for DRM using deep neural networks with smooth activation functions including logistic and hyperbolic tangent functions. Our results show how to set the hyper-parameter of depth and width to achieve the desired convergence rate in terms of the number of training samples. [ABSTRACT FROM AUTHOR]