Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery
arXiv: Machine Learning, Volume abs/1611.07252, 2016.
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
Full Text (Upload PDF)
PPT (Upload PPT)