COVID-19 is an infectious disease that mostly affects the respiratory system. At the time of this research being performed, there were more than 1.4 million cases of COVID-19, and one of the biggest anxieties is not just our health, but our livelihoods, too. In this research, authors investigate the impact of COVID-19 on the global economy, more specifically, the impact of COVID-19 on financial movement of Crude Oil price and three U.S. stock indexes: DJI, S&P 500 and NASDAQ Composite. The proposed system for predicting commodity and stock prices integrates the Stationary Wavelet Transform (SWT) and Bidirectional Long Short-Term Memory (BDLSTM) networks. Firstly, SWT is used to decompose the data into approximation and detail coefficients. After decomposition, data of Crude Oil price and stock market indexes along with COVID-19 confirmed cases were used as input variables for future price movement forecasting. As a result, the proposed system BDLSTM WT-ADA achieved satisfactory results in terms of five-day Crude Oil price forecast.

Recent theoretical work has shown that massively overparameterized neural networks are equivalent to kernel regressors that use Neural Tangent Kernels (NTKs). Experiments show that these kernel methods perform similarly to real neural networks. Here we show that NTK for fully connected networks with ReLU activation is closely related to the standard Laplace kernel. We show theoretically that for normalized data on the hypersphere both kernels have the same eigenfunctions and their eigenvalues decay polynomially at the same rate, implying that their Reproducing Kernel Hilbert Spaces (RKHS) include the same sets of functions. This means that both kernels give rise to classes of functions with the same smoothness properties. The two kernels differ for data off the hypersphere, but experiments indicate that when data is properly normalized these differences are not significant. Finally, we provide experiments on real data comparing NTK and the Laplace kernel, along with a larger class of γ-exponential kernels. We show that these perform almost identically. Our results suggest that much insight about neural networks can be obtained from analysis of the well-known Laplace kernel, which has a simple closed form.

In this paper, we propose a novel network training mechanism called "dynamic channel propagation" to prune the neural networks during the training period. In particular, we pick up a specific group of channels in each convolutional layer to participate in the forward propagation in training time according to the significance level of channel, which is defined as channel utility. The utility values with respect to all selected channels are updated simultaneously with the error back-propagation process and will adaptively change. Furthermore, when the training ends, channels with high utility values are retained whereas those with low utility values are discarded. Hence, our proposed scheme trains and prunes neural networks simultaneously. We empirically evaluate our novel training scheme on various representative benchmark datasets and advanced convolutional neural network (CNN) architectures, including VGGNet and ResNet. The experiment results verify the superior performance and robust effectiveness of our approach.

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. We also notice that such technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique.

With the huge success of deep learning, other machine learning paradigms have had to take back seat. Yet other models, particularly rule-based, are more readable and explainable and can even be competitive when labelled data is not abundant. However, most of the existing rule-based classifiers suffer from the production of a large number of classification rules, affecting the model readability. This hampers the classification accuracy as noisy rules might not add any useful informationfor classification and also lead to longer classification time. In this study, we propose SigD2 which uses a novel, two-stage pruning strategy which prunes most of the noisy, redundant and uninteresting rules and makes the classification model more accurate and readable. To make SigDirect more competitive with the most prevalent but uninterpretable machine learning-based classifiers like neural networks and support vector machines, we propose bagging and boosting on the ensemble of the SigDirect classifier. The results of the proposed algorithms are quite promising and we are able to obtain a minimal set of statistically significant rules for classification without jeopardizing the classification accuracy. We use 15 UCI datasets and compare our approach with eight existing systems.The SigD2 and boosted SigDirect (ACboost) ensemble model outperform various state-of-the-art classifiers not only in terms of classification accuracy but also in terms of the number of rules.

Advancements in sensing and computing technologies, the development of human and computer interaction frameworks, big data storage capabilities, and the emergence of cloud storage and could computing have resulted in an abundance of data in the modern industry. This data availability has encouraged researchers and industry practitioners to rely on data-based machine learning, especially deep learning, models for fault diagnostics and prognostics more than ever. These models provide unique advantages, however, their performance is heavily dependent on the training data and how well that data represents the test data. This issue mandates fine-tuning and even training the models from scratch when there is a slight change in operating conditions or equipment. Transfer learning is an approach that can remedy this issue by keeping portions of what is learned from previous training and transferring them to the new application. In this paper, a unified definition for transfer learning and its different types is provided, Prognostics and Health Management (PHM) studies that have used transfer learning are reviewed in detail, and finally, a discussion on transfer learning application considerations and gaps is provided for improving the applicability of transfer learning in PHM.

We propose an integrated deep-generative framework, that jointly models complementary information from resting-state functional MRI (rs-fMRI) connectivity and diffusion tensor imaging (DTI) tractography to extract predictive biomarkers of a disease. The generative part of our framework is a structurally-regularized Dynamic Dictionary Learning (sr-DDL) model that decomposes the dynamic rs-fMRI correlation matrices into a collection of shared basis networks and time varying patient-specific loadings. This matrix factorization is guided by the DTI tractography matrices to learn anatomically informed connectivity profiles. The deep part of our framework is an LSTM-ANN block, which models the temporal evolution of the patient sr-DDL loadings to predict multidimensional clinical severity. Our coupled optimization procedure collectively estimates the basis networks, the patient-specific dynamic loadings, and the neural network weights. We validate our framework on a multi-score prediction task in 57 patients diagnosed with Autism Spectrum Disorder (ASD). Our hybrid model outperforms state-of-the-art baselines in a five-fold cross validated setting and extracts interpretable multimodal neural signatures of brain dysfunction in ASD.

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various techniques have been proposed since the original formulation, which mimic different aspects of the teacher such as the representation space, decision boundary, or intra-data relationship. Some methods replace the one-way knowledge distillation from a static teacher with collaborative learning between a cohort of students. Despite the recent advances, a clear understanding of where knowledge resides in a deep neural network and an optimal method for capturing knowledge from teacher and transferring it to student remains an open question. In this study, we provide an extensive study on nine different KD methods which covers a broad spectrum of approaches to capture and transfer knowledge. We demonstrate the versatility of the KD framework on different datasets and network architectures under varying capacity gaps between the teacher and student. The study provides intuition for the effects of mimicking different aspects of the teacher and derives insights from the performance of the different distillation approaches to guide the design of more effective KD methods. Furthermore, our study shows the effectiveness of the KD framework in learning efficiently under varying severity levels of label noise and class imbalance, consistently providing generalization gains over standard training. We emphasize that the efficacy of KD goes much beyond a model compression technique and it should be considered as a general-purpose training paradigm which offers more robustness to common challenges in the real-world datasets compared to the standard training procedure.

Data-driven models for predicting dynamic responses of linear and nonlinear systems are of great importance due to their wide application from probabilistic analysis to inverse problems such as system identification and damage diagnosis. In this study, a physics-based recurrent neural network model is designed that is able to learn the dynamics of linear and nonlinear multiple degrees of freedom systems given a ground motion. The model is able to estimate a complete set of responses, including displacement, velocity, acceleration, and internal forces. Compared to the most advanced counterparts, this model requires a smaller number of trainable variables while the accuracy of predictions is higher for long trajectories. In addition, the architecture of the recurrent block is inspired by differential equation solver algorithms and it is expected that this approach yields more generalized solutions. In the training phase, we propose multiple novel techniques to dramatically accelerate the learning process using smaller datasets, such as hardsampling, utilization of trajectory loss function, and implementation of a trust-region approach. Numerical case studies are conducted to examine the strength of the network to learn different nonlinear behaviors. It is shown that the network is able to capture different nonlinear behaviors of dynamic systems with very high accuracy and with no need for prior information or very large datasets.

We propose a novel interpretable recurrent neural network (RNN) model, called ProtoryNet, in which we introduce a new concept of prototype trajectories. Motivated by the prototype theory in modern linguistics, ProtoryNet makes a prediction by finding the most similar prototype for each sentence in a text sequence and feeding an RNN backbone with the proximity of each of the sentences to the prototypes. The RNN backbone then captures the temporal pattern of the prototypes, to which we refer as prototype trajectories. The prototype trajectories enable intuitive, fine-grained interpretation of how the model reached to the final prediction, resembling the process of how humans analyze paragraphs. Experiments conducted on multiple public data sets reveal that the proposed method not only is more interpretable but also is more accurate than the current state-of-the-art prototype-based method. Furthermore, we report a survey result indicating that human users find ProtoryNet more intuitive and easier to understand, compared to the other prototype-based methods.