Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable balance between denoising performance and computational cost in real scenarios. In this study, we propose a novel parameter pruning (PP) technique, which removes redundant channels in a neural network. In addition, a parameter quantization (PQ) technique was applied to reduce the size of a neural network by representing weights with fewer cluster centroids. Because the techniques are derived based on different concepts, the PP and PQ can be integrated to provide even more compact SE models. The experimental results show that the PP and PQ techniques produce a compacted SE model with a size of only 10.03% compared to that of the original model, resulting in minor performance losses of 1.43% (from 0.70 to 0.69) for STOI and 3.24% (from 1.85 to 1.79) for PESQ. The promising results suggest that the PP and PQ techniques can be used in a SE system in devices with limited storage and computation resources.

Electronic Health Records (EHRs) have been heavily used to predict various downstream clinical tasks such as readmission or mortality. One of the modalities in EHRs, clinical notes, has not been fully explored for these tasks due to its unstructured and inexplicable nature. Although recent advances in deep learning (DL) enables models to extract interpretable features from unstructured data, they often require a large amount of training data. However, many tasks in medical domains inherently consist of small sample data with lengthy documents; for a kidney transplant as an example, data from only a few thousand of patients are available and each patient's document consists of a couple of millions of words in major hospitals. Thus, complex DL methods cannot be applied to these kinds of domains. In this paper, we present a comprehensive ensemble model using vector space modeling and topic modeling. Our proposed model is evaluated on the readmission task of kidney transplant patients and improves 0.0211 in terms of c-statistics from the previous state-of-the-art approach using structured data, while typical DL methods fail to beat this approach. The proposed architecture provides the interpretable score for each feature from both modalities, structured and unstructured data, which is shown to be meaningful through a physician's evaluation.

Time series anomaly detection plays a critical role in automated monitoring systems. Most previous deep learning efforts related to time series anomaly detection were based on recurrent neural networks (RNN). In this paper, we propose a time series segmentation approach based on convolutional neural networks (CNN) for anomaly detection. Moreover, we propose a transfer learning framework that pretrains a model on a large-scale synthetic univariate time series data set and then fine-tunes its weights on small-scale, univariate or multivariate data sets with previously unseen classes of anomalies. For the multivariate case, we introduce a novel network architecture. The approach was tested on multiple synthetic and real data sets successfully.

The measurement of time is central to intelligent behavior. We know that both animals and artificial agents can successfully use temporal dependencies to select actions. In artificial agents, little work has directly addressed (1) which architectural components are necessary for successful development of this ability, (2) how this timing ability comes to be represented in the units and actions of the agent, and (3) whether the resulting behavior of the system converges on solutions similar to those of biology. Here we studied interval timing abilities in deep reinforcement learning agents trained end-to-end on an interval reproduction paradigm inspired by experimental literature on mechanisms of timing. We characterize the strategies developed by recurrent and feedforward agents, which both succeed at temporal reproduction using distinct mechanisms, some of which bear specific and intriguing similarities to biological systems. These findings advance our understanding of how agents come to represent time, and they highlight the value of experimentally inspired approaches to characterizing agent abilities.

Recently, deep models have had considerable success in several tasks, especially with low-level representations. However, effective learning from sparse noisy samples is a major challenge in most deep models, especially in domains with structured representations. Inspired by the proven success of human guided machine learning, we propose Knowledge-augmented Column Networks, a relational deep learning framework that leverages human advice/knowledge to learn better models in presence of sparsity and systematic noise.

The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commonsense reasoning. We show that the attentions produced by BERT can be directly utilized for tasks such as the Pronoun Disambiguation Problem and Winograd Schema Challenge. Our proposed attention-guided commonsense reasoning method is conceptually simple yet empirically powerful. Experimental analysis on multiple datasets demonstrates that our proposed system performs remarkably well on all cases while outperforming the previously reported state of the art by a margin. While results suggest that BERT seems to implicitly learn to establish complex relationships between entities, solving commonsense reasoning tasks might require more than unsupervised models learned from huge text corpora.

Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the weights until the steady state of output neurons coincides with a target y. Convergent RNNs can also be trained with the more conventional Backpropagation Through Time (BPTT) algorithm. In its original formulation EP was described in the case of real-time neuronal dynamics, which is computationally costly. In this work, we introduce a discrete-time version of EP with simplified equations and with reduced simulation time, bringing EP closer to practical machine learning tasks. We first prove theoretically, as well as numerically that the neural and weight updates of EP, computed by forward-time dynamics, are step-by-step equal to the ones obtained by BPTT, with gradients computed backward in time. The equality is strict when the transition function of the dynamics derives from a primitive function and the steady state is maintained long enough. We then show for more standard discrete-time neural network dynamics that the same property is approximately respected and we subsequently demonstrate training with EP with equivalent performance to BPTT. In particular, we define the first convolutional architecture trained with EP achieving ~ 1% test error on MNIST, which is the lowest error reported with EP. These results can guide the development of deep neural networks trained with EP.

The capability to perform facial analysis from video sequences has significant potential to positively impact in many areas of life. One such area relates to the medical domain to specifically aid in the diagnosis and rehabilitation of patients with facial palsy. With this application in mind, this paper presents an end-to-end framework, named 3DPalsyNet, for the tasks of mouth motion recognition and facial palsy grading. 3DPalsyNet utilizes a 3D CNN architecture with a ResNet backbone for the prediction of these dynamic tasks. Leveraging transfer learning from a 3D CNNs pre-trained on the Kinetics data set for general action recognition, the model is modified to apply joint supervised learning using center and softmax loss concepts. 3DPalsyNet is evaluated on a test set consisting of individuals with varying ranges of facial palsy and mouth motions and the results have shown an attractive level of classification accuracy in these task of 82% and 86% respectively. The frame duration and the loss function affect was studied in terms of the predictive qualities of the proposed 3DPalsyNet, where it was found shorter frame duration's of 8 performed best for this specific task. Centre loss and softmax have shown improvements in spatio-temporal feature learning than softmax loss alone, this is in agreement with earlier work involving the spatial domain.

Automatic estimation of relative difficulty of a pair of questions is an important and challenging problem in community question answering (CQA) services. There are limited studies which addressed this problem. Past studies mostly leveraged expertise of users answering the questions and barely considered other properties of CQA services such as metadata of users and posts, temporal information and textual content. In this paper, we propose DiffQue, a novel system that maps this problem to a network-aided edge directionality prediction problem. DiffQue starts by constructing a novel network structure that captures different notions of difficulties among a pair of questions. It then measures the relative difficulty of two questions by predicting the direction of a (virtual) edge connecting these two questions in the network. It leverages features extracted from the network structure, metadata of users/posts and textual description of questions and answers. Experiments on datasets obtained from two CQA sites (further divided into four datasets) with human annotated ground-truth show that DiffQue outperforms four state-of-the-art methods by a significant margin (28.77% higher F1 score and 28.72% higher AUC than the best baseline). As opposed to the other baselines, (i) DiffQue appropriately responds to the training noise, (ii) DiffQue is capable of adapting multiple domains (CQA datasets), and (iii) DiffQue can efficiently handle 'cold start' problem which may arise due to the lack of information for newly posted questions or newly arrived users.

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system. Existing approaches mostly capture the spatial dependency on a fixed graph structure, assuming that the underlying relation between entities is pre-determined. However, the explicit graph structure (relation) does not necessarily reflect the true dependency and genuine relation may be missing due to the incomplete connections in the data. Furthermore, existing methods are ineffective to capture the temporal trends as the RNNs or CNNs employed in these methods cannot capture long-range temporal sequences. To overcome these limitations, we propose in this paper a novel graph neural network architecture, Graph WaveNet, for spatial-temporal graph modeling. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data. With a stacked dilated 1D convolution component whose receptive field grows exponentially as the number of layers increases, Graph WaveNet is able to handle very long sequences. These two components are integrated seamlessly in a unified framework and the whole framework is learned in an end-to-end manner. Experimental results on two public traffic network datasets, METR-LA and PEMS-BAY, demonstrate the superior performance of our algorithm.