← Search

Thomas Powers

2 accepted papers

2017

Building recurrent networks by unfolding iterative thresholding for sequential sparse recovery

ICASSP 2017accepted

Historically, sparse methods and neural networks, particularly modern deep learning methods, have been relatively disparate areas. Sparse methods are typically used for signal enhancement, compression, and recovery, usually in an unsupervised framework, while neural networks commonly rely on a super…

Cited by 0SourceScholar
2016

Full-Capacity Unitary Recurrent Neural Networks

NeurIPS 2016poster

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recurrence matrices, have recently been proposed as a means to avoid these issues. H…