Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery

arXiv: Machine Learning, Volume abs/1611.07252, 2016.

Cited by: 17|Bibtex|Views52
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding algorithm (SISTA) for solving th...More

Code:

Data:

Your rating :
0

 

Tags
Comments