Now showing items 1-2 of 2
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
(Center for Brains, Minds and Machines (CBMM), arXiv, 2017-04-03)
Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the ...
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
(Center for Brains, Minds and Machines (CBMM), arXiv, 2017-03-01)
While great strides have been made in using deep learning algorithms to solve supervised learning tasks, the problem of unsupervised learning—leveraging unlabeled examples to learn about the structure of a domain — remains ...