Visualizing Neural Network Imagination
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917662745952256 |
|---|---|
| author | Wichers, Nevan Tao, Victor Volpato, Riccardo Barez, Fazl |
| author_facet | Wichers, Nevan Tao, Victor Volpato, Riccardo Barez, Fazl |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_06409 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Visualizing Neural Network Imagination Wichers, Nevan Tao, Victor Volpato, Riccardo Barez, Fazl Machine Learning Artificial Intelligence 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. |
| title | Visualizing Neural Network Imagination |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2405.06409 |