Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks

Ramin M. Hasani, Alexander Amini, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus

Oct 31, 2018 NIPS 2018 Workshop IRASL Blind Submission readers: everyone
  • Abstract: In this paper, we introduce a novel method to interpret recurrent neural networks (RNNs), particularly long short-term memory networks (LSTMs) at the cellular level. We propose a systematic pipeline for interpreting individual hidden state dynamics within the network using response characterization methods. The ranked contribution of individual cells to the network's output is computed by analyzing a set of interpretable metrics of their decoupled step and sinusoidal responses. As a result, our method is able to uniquely identify neurons with insightful dynamics, quantify relationships between dynamical properties and test accuracy through ablation analysis, and interpret the impact of network capacity on a network's dynamical distribution. Finally, we demonstrate generalizability and scalability of our method by evaluating a series of different benchmark sequential datasets.
  • Keywords: Interpretability, recurrent neural networks, long short-term memory, dynamical systems, response characterization method
  • TL;DR: Introducing the response charactrization method for interpreting cell dynamics in learned long short-term memory (LSTM) networks.
0 Replies