Deep-layered machines have a built-in Occam's razor
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908859136737280 |
|---|---|
| author | Fink, Thomas M. A. |
| author_facet | Fink, Thomas M. A. |
| contents | Input-output maps are prevalent throughout science and technology. They are empirically observed to be biased towards simple outputs, but we don't understand why. To address this puzzle, we study the archetypal input-output map: a deep-layered machine in which every node is a Boolean function of all the nodes below it. We give an exact theory for the distribution of outputs, and we confirm our predictions through extensive computer experiments. As the network depth increases, the distribution becomes exponentially biased towards simple outputs. This suggests that deep-layered machines and other learning methodologies may be inherently biased towards simplicity in the models that they generate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_01217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deep-layered machines have a built-in Occam's razor Fink, Thomas M. A. Disordered Systems and Neural Networks Cellular Automata and Lattice Gases Input-output maps are prevalent throughout science and technology. They are empirically observed to be biased towards simple outputs, but we don't understand why. To address this puzzle, we study the archetypal input-output map: a deep-layered machine in which every node is a Boolean function of all the nodes below it. We give an exact theory for the distribution of outputs, and we confirm our predictions through extensive computer experiments. As the network depth increases, the distribution becomes exponentially biased towards simple outputs. This suggests that deep-layered machines and other learning methodologies may be inherently biased towards simplicity in the models that they generate. |
| title | Deep-layered machines have a built-in Occam's razor |
| topic | Disordered Systems and Neural Networks Cellular Automata and Lattice Gases |
| url | https://arxiv.org/abs/2603.01217 |