Towards Robust Deep Neural Networks

no code implementations • 27 Oct 2018 • Timothy E. Wang, Yiming Gu, Dhagash Mehta, Xiaojun Zhao, Edgar A. Bernal

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks.

Adversarial Robustness

The Loss Surface of XOR Artificial Neural Networks

no code implementations • 6 Apr 2018 • Dhagash Mehta, Xiaojun Zhao, Edgar A. Bernal, David J. Wales

Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters.