Pruning Increases Orderedness in Recurrent Computation
Fuente:
arXiv
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916852318339072 |
|---|---|
| author | Song, Yiding |
| author_facet | Song, Yiding |
| contents | Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information flow between neurons, we formalise a perceptron layer with all-to-all connections (mathematically equivalent to a weight-tied recurrent neural network) and demonstrate that directionality, a hallmark of modern feed-forward networks, can be induced rather than hard-wired by applying appropriate pruning techniques. Across different random seeds our pruning schemes successfully induce greater topological ordering in information flow between neurons without compromising performance, suggesting that directionality is not a prerequisite for learning, but may be an advantageous inductive bias discoverable by gradient descent and sparsification. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14747 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pruning Increases Orderedness in Recurrent Computation Song, Yiding Machine Learning Neural and Evolutionary Computing Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information flow between neurons, we formalise a perceptron layer with all-to-all connections (mathematically equivalent to a weight-tied recurrent neural network) and demonstrate that directionality, a hallmark of modern feed-forward networks, can be induced rather than hard-wired by applying appropriate pruning techniques. Across different random seeds our pruning schemes successfully induce greater topological ordering in information flow between neurons without compromising performance, suggesting that directionality is not a prerequisite for learning, but may be an advantageous inductive bias discoverable by gradient descent and sparsification. |
| title | Pruning Increases Orderedness in Recurrent Computation |
| topic | Machine Learning Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2507.14747 |