The continued success of Deep Neural Networks (DNNs) in classification tasks has sparked a trend of accelerating their execution with specialized hardware. While published designs …
We combine Riemannian geometry with the mean field theory of high dimensional chaos to study the nature of signal propagation in deep neural networks with random weights. Our …
Systolic Arrays are one of the most popular compute substrates within Deep Learning accelerators today, as they provide extremely high efficiency for running dense matrix …
We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack …
D Neil, M Pfeiffer, SC Liu - Advances in neural information …, 2016 - proceedings.neurips.cc
Abstract Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns from temporal sequences. Current RNN models are ill suited to process …
X Ding, Q He - IEEE Transactions on Instrumentation and …, 2017 - ieeexplore.ieee.org
Considering various health conditions under varying operational conditions, the mining sensitive feature from the measured signals is still a great challenge for intelligent fault …
X Li, S Chen, X Hu, J Yang - … of the IEEE/CVF conference on …, 2019 - openaccess.thecvf.com
This paper first answers the question" why do the two most powerful techniques Dropout and Batch Normalization (BN) often lead to a worse performance when they are combined …
Y Miao, M Gowayyed, F Metze - 2015 IEEE workshop on …, 2015 - ieeexplore.ieee.org
The performance of automatic speech recognition (ASR) has improved tremendously due to the application of deep neural networks (DNNs). Despite this progress, building a new ASR …
Motivated by the variance in the numerical precision requirements of Deep Neural Networks (DNNs)[1],[2], Stripes (STR), a hardware accelerator is presented whose execution time …