LGAIMay 10, 2024

Visualizing Neural Network Imagination

arXiv:2405.06409v1h-index: 15
Originality Synthesis-oriented
AI Analysis

This work addresses interpretability for neural network researchers, but it is incremental as it focuses on a simple task.

The paper tackled the problem of visualizing environment states represented in neural network hidden activations by using a decoder network and new techniques, achieving high interpretability on a simple task as measured by a quantitative metric.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes