Deep Learning

We investigate deep learning, which is a way to train deep neural networks (neural networks with many layers) to solve complicated tasks. Deep neural networks are capable of translating spoken words to text, translating between languages, and recognizing objects in pictures. While deep neural networks have recently been shown to perform mind-blowing feats, they remain mostly black boxes whose inner workings we do not understand. Our research focuses on shedding light into these black boxes to understand what they learn and how they perform so well. See below for papers on how we do that.


Videos

Deep Neural Networks are Easily Fooled

This video accompanies the following paper(s):

PPGN: Sampling within a single class of Junco

This video accompanies the following paper(s):

PPGN: Sampling between 10 classes

This video accompanies the following paper(s):

Deep Learning Overview & Visualizing What Deep Neural Networks Learn

This video accompanies the following paper(s):

Convergent Learning: Do different neural networks learn the same representations?

This video accompanies the following paper(s):

Understanding Neural Networks Through Deep Visualization

This video accompanies the following paper(s):

PPGN: Sampling within a single class of Triumph Arch

This video accompanies the following paper(s):

Deep Neural Networks are Easily Fooled

PPGN: Sampling within a single class of Junco

PPGN: Sampling between 10 classes

Deep Learning Overview & Visualizing What Deep Neural Networks Learn

Convergent Learning: Do different neural networks learn the same representations?

Understanding Neural Networks Through Deep Visualization

PPGN: Sampling within a single class of Triumph Arch


Publications