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.
@article{arxiv.2405.06409,
title = {Visualizing Neural Network Imagination},
author = {Nevan Wichers and Victor Tao and Riccardo Volpato and Fazl Barez},
journal= {arXiv preprint arXiv:2405.06409},
year = {2024}
}