How Can Neuroscience Help Us Build More Robust Deep Neural Networks?

Sayanton V. Dibbo, Siddharth Mansingh, Jocelyn Rego, Garrett T. Kenyon, Juston Moore, Michael Teti

Keywords: deep neural networks, adversarial machine learning, sparse coding, energy-based models

TL;DR: We discuss how neuroscience can benefit the current field of adversarial machine learning.

Abstract: Although Deep Neural Networks (DNNs) are often compared to biological visual systems, they are far less robust to natural and adversarial examples. In contrast, biological visual systems can reliably recognize different objects under a variety of settings. While recent innovations have closed the performance gap between biological and artificial vision systems to some extent, there are still many practical differences between the two. In this Blue Sky Ideas presentation, we will identify some key differences between standard DNNs and biological perceptual systems that may contribute to this lack of robustness. We will then present recent work on biologically-plausible, robust DNNs that are derived from and can be easily implemented on physical systems/neuromorphic hardware.

Submission Number: 77