A Proposal for Networks Capable of Continual Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909555905003520 |
|---|---|
| author | Erden, Zeki Doruk Faltings, Boi |
| author_facet | Erden, Zeki Doruk Faltings, Boi |
| contents | We analyze the ability of computational units to retain past responses after parameter updates, a key property for system-wide continual learning. Neural networks trained with gradient descent lack this capability, prompting us to propose Modelleyen, an alternative approach with inherent response preservation. We demonstrate through experiments on modeling the dynamics of a simple environment and on MNIST that, despite increased computational complexity and some representational limitations at its current stage, Modelleyen achieves continual learning without relying on sample replay or predefined task boundaries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22068 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Proposal for Networks Capable of Continual Learning Erden, Zeki Doruk Faltings, Boi Machine Learning Artificial Intelligence We analyze the ability of computational units to retain past responses after parameter updates, a key property for system-wide continual learning. Neural networks trained with gradient descent lack this capability, prompting us to propose Modelleyen, an alternative approach with inherent response preservation. We demonstrate through experiments on modeling the dynamics of a simple environment and on MNIST that, despite increased computational complexity and some representational limitations at its current stage, Modelleyen achieves continual learning without relying on sample replay or predefined task boundaries. |
| title | A Proposal for Networks Capable of Continual Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.22068 |