Recent & Upcoming Talks

The t-distributed Stochastic Neighbor Embedding (t-SNE) algorithm is a ubiquitously employed dimensionality reduction (DR) method. Its …

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This …

a.k.a. “Why should you bother to have an internship during your Ph.D.?”

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust …

Recent Publications

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This …

This brief discusses the simple idea that dropout regularization can be used to efficiently induce resiliency to missing inputs at …

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust …

Contact