From pixels to planning: scale-free active inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914891827249152 |
|---|---|
| author | Friston, Karl Heins, Conor Verbelen, Tim Da Costa, Lancelot Salvatori, Tommaso Markovic, Dimitrije Tschantz, Alexander Koudahl, Magnus Buckley, Christopher Parr, Thomas |
| author_facet | Friston, Karl Heins, Conor Verbelen, Tim Da Costa, Lancelot Salvatori, Tommaso Markovic, Dimitrije Tschantz, Alexander Koudahl, Magnus Buckley, Christopher Parr, Thomas |
| contents | This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to include paths as latent variables, rendering it suitable for active inference and learning in a dynamic setting. Specifically, we consider deep or hierarchical forms using the renormalisation group. The ensuing renormalising generative models (RGM) can be regarded as discrete homologues of deep convolutional neural networks or continuous state-space models in generalised coordinates of motion. By construction, these scale-invariant models can be used to learn compositionality over space and time, furnishing models of paths or orbits; i.e., events of increasing temporal depth and itinerancy. This technical note illustrates the automatic discovery, learning and deployment of RGMs using a series of applications. We start with image classification and then consider the compression and generation of movies and music. Finally, we apply the same variational principles to the learning of Atari-like games. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20292 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From pixels to planning: scale-free active inference Friston, Karl Heins, Conor Verbelen, Tim Da Costa, Lancelot Salvatori, Tommaso Markovic, Dimitrije Tschantz, Alexander Koudahl, Magnus Buckley, Christopher Parr, Thomas Machine Learning Neurons and Cognition 92 F.1.1 This paper describes a discrete state-space model -- and accompanying methods -- for generative modelling. This model generalises partially observed Markov decision processes to include paths as latent variables, rendering it suitable for active inference and learning in a dynamic setting. Specifically, we consider deep or hierarchical forms using the renormalisation group. The ensuing renormalising generative models (RGM) can be regarded as discrete homologues of deep convolutional neural networks or continuous state-space models in generalised coordinates of motion. By construction, these scale-invariant models can be used to learn compositionality over space and time, furnishing models of paths or orbits; i.e., events of increasing temporal depth and itinerancy. This technical note illustrates the automatic discovery, learning and deployment of RGMs using a series of applications. We start with image classification and then consider the compression and generation of movies and music. Finally, we apply the same variational principles to the learning of Atari-like games. |
| title | From pixels to planning: scale-free active inference |
| topic | Machine Learning Neurons and Cognition 92 F.1.1 |
| url | https://arxiv.org/abs/2407.20292 |