Covariance estimation is ubiquitous in functional data analysis. Yet, the case of functional observations over multidimensional domains introduces computational and statistical challenges, rendering the standard methods effectively inapplicable. To address this problem, we introduce Covariance Networks (CovNet) as a modeling and estimation tool. The CovNet model is universal -- it can be used to approximate any covariance up to desired precision. Moreover, the model can be fitted efficiently to the data and its neural network architecture allows us to employ modern computational tools in the implementation. The CovNet model also admits a closed-form eigen-decomposition, which can be computed efficiently, without constructing the covariance itself. This facilitates easy storage and subsequent manipulation in the context of the CovNet. Moreover, we establish consistency of the proposed estimator and derive its rate of convergence. The usefulness of the proposed method is demonstrated by means of an extensive simulation study.

It is well known that recurrent neural networks (RNNs) faced limitations in learning long-term dependencies that have been addressed by memory structures in long short-term memory (LSTM) networks. Matrix neural networks feature matrix representation which inherently preserves the spatial structure of data and has the potential to provide better memory structures when compared to canonical neural networks that use vector representation. Neural Turing machines (NTMs) are novel RNNs that implement notion of programmable computers with neural network controllers to feature algorithms that have copying, sorting, and associative recall tasks. In this paper, we study the augmentation of memory capacity with a matrix representation of RNNs and NTMs (MatNTMs). We investigate if matrix representation has a better memory capacity than the vector representations in conventional neural networks. We use a probabilistic model of the memory capacity using Fisher information and investigate how the memory capacity for matrix representation networks are limited under various constraints, and in general, without any constraints. In the case of memory capacity without any constraints, we found that the upper bound on memory capacity to be $N^2$ for an $N\times N$ state matrix. The results from our experiments using synthetic algorithmic tasks show that MatNTMs have a better learning capacity when compared to its counterparts.

This paper models residential consumers' energy-consumption behavior by load patterns and distributions and reveals the relationship between consumers' load patterns and socioeconomic features by machine learning. We analyze the real-world smart meter data and extract load patterns using K-Medoids clustering, which is robust to outliers. We develop an analytical framework with feature selection and deep learning models to estimate the relationship between load patterns and socioeconomic features. Specifically, we use an entropy-based feature selection method to identify the critical socioeconomic characteristics that affect load patterns and benefit our method's interpretability. We further develop a customized deep neural network model to characterize the relationship between consumers' load patterns and selected socioeconomic features. Numerical studies validate our proposed framework using Pecan Street smart meter data and survey. We demonstrate that our framework can capture the relationship between load patterns and socioeconomic information and outperform benchmarks such as regression and single DNN models.

The remaining Useful Life (RUL) of equipment is defined as the duration between the current time and its failure. An accurate and reliable prognostic of the remaining useful life provides decision-makers with valuable information to adopt an appropriate maintenance strategy to maximize equipment utilization and avoid costly breakdowns. In this work, we propose an end-to-end deep learning model based on multi-layer perceptron and long short-term memory layers (LSTM) to predict the RUL. After normalization of all data, inputs are fed directly to an MLP layers for feature learning, then to an LSTM layer to capture temporal dependencies, and finally to other MLP layers for RUL prognostic. The proposed architecture is tested on the NASA commercial modular aero-propulsion system simulation (C-MAPSS) dataset. Despite its simplicity with respect to other recently proposed models, the model developed outperforms them with a significant decrease in the competition score and in the root mean square error score between the predicted and the gold value of the RUL. In this paper, we will discuss how the proposed end-to-end model is able to achieve such good results and compare it to other deep learning and state-of-the-art methods.

This paper discusses the need of an automated system for detecting print errors and the efficacy of Convolutional Neural Networks in such an application. We recognise the need of a dataset containing print error samples and propose a way to generate one artificially. We discuss the algorithms to generate such data along with the limitaions and advantages of such an apporach. Our final trained network gives a remarkable accuracy of 99.83\% in testing. We further evaluate how such efficiency was achieved and what modifications can be tested to further the results.

Tensor Decomposition Networks(TDNs) prevail for their inherent compact architectures. For providing convenience, we present a toolkit named TedNet that is based on the Pytorch framework, to give more researchers a flexible way to exploit TDNs. TedNet implements 5 kinds of tensor decomposition(i.e., CANDECOMP/PARAFAC(CP), Block-Term Tucker(BT), Tucker-2, Tensor Train(TT) and Tensor Ring(TR)) on traditional deep neural layers, the convolutional layer and the fully-connected layer. By utilizing these basic layers, it is simple to construct a variety of TDNs like TR-ResNet, TT-LSTM, etc. TedNet is available at https://github.com/tnbar/tednet.

Although recent advances in deep learning accelerated an improvement in a weakly supervised object localization (WSOL) task, there are still challenges to identify the entire body of an object, rather than only discriminative parts. In this paper, we propose a novel residual fine-grained attention (RFGA) module that autonomously excites the less activated regions of an object by utilizing information distributed over channels and locations within feature maps in combination with a residual operation. To be specific, we devise a series of mechanisms of triple-view attention representation, attention expansion, and feature calibration. Unlike other attention-based WSOL methods that learn a coarse attention map, having the same values across elements in feature maps, our proposed RFGA learns fine-grained values in an attention map by assigning different attention values for each of the elements. We validated the superiority of our proposed RFGA module by comparing it with the recent methods in the literature over three datasets. Further, we analyzed the effect of each mechanism in our RFGA and visualized attention maps to get insights.

Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every single sentence, while ellipsis and anaphora frequently occur in dialogues. To address this problem, we propose the conversational SRL task, where an argument can be the dialogue participants, a phrase in the dialogue history or the current sentence. As the existing SRL datasets are in the sentence level, we manually annotate semantic roles for 3,000 chit-chat dialogues (27,198 sentences) to boost the research in this direction. Experiments show that while traditional SRL systems (even with the help of coreference resolution or rewriting) perform poorly for analyzing dialogues, modeling dialogue histories and participants greatly helps the performance, indicating that adapting SRL to conversations is very promising for universal dialogue understanding. Our initial study by applying CSRL to two mainstream conversational tasks, dialogue response generation and dialogue context rewriting, also confirms the usefulness of CSRL.

We propose an enhancement technique of the Class Activation Mapping methods like Grad-CAM or Excitation Backpropagation, which presents visual explanations of decisions from CNN-based models. Our idea, called Gradual Extrapolation, can supplement any method that generates a heatmap picture by sharpening the output. Instead of producing a coarse localization map highlighting the important predictive regions in the image, our method outputs the specific shape that most contributes to the model output. Thus, it improves the accuracy of saliency maps. Effect has been achieved by gradual propagation of the crude map obtained in deep layer through all preceding layers with respect to their activations. In validation tests conducted on a selected set of images, the proposed method significantly improved the localization detection of the neural networks' attention. Furthermore, the proposed method is applicable to any deep neural network model.

Scientific publications play a vital role in the career of a researcher. However, some articles become more popular than others among the research community and subsequently drive future research directions. One of the indicative signs of popular articles is the number of citations an article receives. The citation count, which is also the basis with various other metrics, such as the journal impact factor score, the $h$-index, is an essential measure for assessing a scientific paper's quality. In this work, we proposed a Graph Convolutional Network (GCN) based framework for estimating future research publication citations for both the short-term (1-year) and long-term (for 5-years and 10-years) duration. We have tested our proposed approach over the AMiner dataset, specifically on research articles from the computer science domain, consisting of more than 0.8 million articles.