Ewout Van Den Berg — accepted AI-conference papers

2019

Estimating Information Flow in Deep Neural Networks

Ziv Goldfeld, Ewout Van Den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury +1

ICML 2019oral

We study the estimation of the mutual information I(X;T_$\ell$) between the input X to a deep neural network (DNN) and the output vector T_$\ell$ of its $\ell$-th hidden layer (an “internal representation”). Focusing on feedforward networks with fixed weights and noisy internal representations, we d…

Cited by 181 Source ↗PDF ↗Scholar ↗

2017

Training variance and performance evaluation of neural networks in speech

Ewout van den Berg, Bhuvana Ramabhadran, Michael Picheny

ICASSP 2017accepted

In this work we study variance in the results of neural network training on a wide variety of configurations in automatic speech recognition. Although this variance itself is well known, this is, to the best of our knowledge, the first paper that performs an extensive empirical study on its effects…

Cited by 0 Source ↗Scholar ↗