Autor: |
Wichers, Nevan, Tao, Victor, Volpato, Riccardo, Barez, Fazl |
Rok vydání: |
2024 |
Předmět: |
|
Druh dokumentu: |
Working Paper |
Popis: |
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. |
Databáze: |
arXiv |
Externí odkaz: |
|