Search Results for author: Matthew Emigh

Found 2 papers, 0 papers with code

Exploiting Spatio-Temporal Structure with Recurrent Winner-Take-All Networks

no code implementations31 Oct 2016 Eder Santana, Matthew Emigh, Pablo Zegers, Jose C. Principe

We propose a convolutional recurrent neural network, with Winner-Take-All dropout for high dimensional unsupervised feature learning in multi-dimensional time series.

Object Recognition Time Series +1

Information Theoretic-Learning Auto-Encoder

no code implementations22 Mar 2016 Eder Santana, Matthew Emigh, Jose C. Principe

We propose Information Theoretic-Learning (ITL) divergence measures for variational regularization of neural networks.

Cannot find the paper you are looking for? You can Submit a new open access paper.