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

arXiv: https://arxiv.org/abs/1809.03864 · HTML: https://mlsanity.com/paper/1809.03864/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Liquid Structural State-Space Models](https://mlsanity.com/paper/2209.12951/) (2022)
- [Efficient Dataset Distillation Using Random Feature Approximation](https://mlsanity.com/paper/2210.12067/) (2022)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing](https://mlsanity.com/paper/2103.04909/) (2021)
- [Sparse Flows: Pruning Continuous-depth Models](https://mlsanity.com/paper/2106.12718/) (2021)
- [GoTube: Scalable Stochastic Verification of Continuous-Depth Models](https://mlsanity.com/paper/2107.08467/) (2021)
- [On the Forward Invariance of Neural ODEs](https://mlsanity.com/paper/2210.04763/) (2022)
- [Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap](https://mlsanity.com/paper/2210.04303/) (2022)
- [Entangled Residual Mappings](https://mlsanity.com/paper/2206.01261/) (2022)
- [Interpreting Neural Policies with Disentangled Tree Representations](https://mlsanity.com/paper/2210.06650/) (2022)

## Abstract (arXiv)

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.