We propose a reconfigurable hardware architecture for deep neural networks (DNNs) capable of online training and inference, which uses algorithmically pre-determined, structured sparsity to significantly lower memory and computational requirements. This novel architecture introduces the notion of edge-processing to provide flexibility and combines junction pipelining and operational paralleliza...

Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success solving them. Despite their success, little is known about robustness to adversarial attacks. In this paper, we propose a novel framework referred as Time-Series Attacks via STATistical Features (TSA-STAT). To address the unique challenges of time-series domain,...

In this paper, we propose training very deep neural networks (DNNs) for supervised learning of hash codes. Existing methods in this context train relatively “shallow” networks limited by the issues arising in back propagation (e.g. vanishing gradients) as well as computational efficiency. We propose a novel and efficient training algorithm inspired by alternating direction method of multipliers...

The idea of using Feed-Forward Neural Networks (FFNNs) as regression functions for Nonlinear AutoRegressive eXogenous (NARX) models, leading to models herein named NARXs (NNARXs), has been quite popular in the early days machine learning applied nonlinear system identification, owing their simple structure and ease application control design. Nonetheless, few theoretical results are available c...

Deep Neural Networks (DNNs) are known as effective model to perform cognitive tasks. However, DNNs are computationally expensive in both train and inference modes as they require the precision of floating point operations. Although, several prior work proposed approximate hardware to accelerate DNNs inference, they have not considered the impact of training on accuracy. In this paper, we propos...

Some recent works revealed that deep neural networks (DNNs) are vulnerable to so-called adversarial attacks where input examples are intentionally perturbed to fool DNNs. In this work, we revisit the DNN training process that includes adversarial examples into the training dataset so as to improve DNN’s resilience to adversarial attacks, namely, adversarial training. Our experiments show that d...