Visualizing Neural Network Imagination

Nevan Wichers, Victor Tao, Riccardo Volpato, Fazl Barez

Keywords: Interpretability, deception, Visualisation

TL;DR: Visualize RNN hidden state representations

Abstract: In certain situations, neural networks will represent environment states in their hidden activations. Our goal is to visualize what environment states the networks are representing. We experiment with a recurrent neural network (RNN) architecture with a decoder network at the end. After training, we apply the decoder to the intermediate representations of the network to visualize what they represent. We define a quantitative interpretability metric and use it to demonstrate that hidden states can be highly interpretable on a simple task. We also develop autoencoder and adversarial techniques and show that benefit interpretability.

Submission Number: 124