Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.02402 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915091937492992 |
|---|---|
| author | Aguiar, Henrique Reis Hennig, Matthias H. |
| author_facet | Aguiar, Henrique Reis Hennig, Matthias H. |
| contents | Lateral inhibition models coupled with Hebbian plasticity have been shown to learn factorised causal representations of input stimuli, for instance, oriented edges are learned from natural images. Currently, these models require the recurrent dynamics to settle into a stable state before weight changes can be applied, which is not only biologically implausible, but also impractical for real-time learning systems. Here, we propose a new Hebbian learning rule which is implemented using plausible biological mechanisms that have been observed experimentally. We find that this rule allows for efficient, time-continuous learning of factorised representations, very similar to the classic noncontinuous Hebbian/anti-Hebbian learning. Furthermore, we show that this rule naturally prevents catastrophic forgetting when stimuli from different distributions are shown sequentially. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Asynchronous Hebbian/anti-Hebbian networks Aguiar, Henrique Reis Hennig, Matthias H. Neurons and Cognition Lateral inhibition models coupled with Hebbian plasticity have been shown to learn factorised causal representations of input stimuli, for instance, oriented edges are learned from natural images. Currently, these models require the recurrent dynamics to settle into a stable state before weight changes can be applied, which is not only biologically implausible, but also impractical for real-time learning systems. Here, we propose a new Hebbian learning rule which is implemented using plausible biological mechanisms that have been observed experimentally. We find that this rule allows for efficient, time-continuous learning of factorised representations, very similar to the classic noncontinuous Hebbian/anti-Hebbian learning. Furthermore, we show that this rule naturally prevents catastrophic forgetting when stimuli from different distributions are shown sequentially. |
| title | Asynchronous Hebbian/anti-Hebbian networks |
| topic | Neurons and Cognition |
| url | https://arxiv.org/abs/2501.02402 |