Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917382747848704 |
|---|---|
| author | Yamada, Taiki |
| author_facet | Yamada, Taiki |
| contents | We show that the error-gated Hebbian rule for PCA (EGHR-PCA), a three-factor learning rule equivalent to Oja's subspace rule under Gaussian inputs, can be systematically derived from Oja's subspace rule using frame theory. The global third factor in EGHR-PCA arises exactly as a frame coefficient when the learning rule is expanded with respect to a natural frame on the space of symmetric matrices. This provides a principled, non-heuristic derivation of a biologically plausible learning rule from its mathematically canonical counterpart. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02849 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule Yamada, Taiki Neural and Evolutionary Computing Machine Learning We show that the error-gated Hebbian rule for PCA (EGHR-PCA), a three-factor learning rule equivalent to Oja's subspace rule under Gaussian inputs, can be systematically derived from Oja's subspace rule using frame theory. The global third factor in EGHR-PCA arises exactly as a frame coefficient when the learning rule is expanded with respect to a natural frame on the space of symmetric matrices. This provides a principled, non-heuristic derivation of a biologically plausible learning rule from its mathematically canonical counterpart. |
| title | Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule |
| topic | Neural and Evolutionary Computing Machine Learning |
| url | https://arxiv.org/abs/2604.02849 |