Metraipolis › archive › dc_8af69e8081bf

In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models — arXiv:2608.19514

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19514
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:09.184Z
SHA-256 of the archived text
774d1c40257870ef266cadfb4ee91b753b2a8154aa41e0f6e95aa1e3615f2558
Stable URL of this page
https://metraipolis.com/documento/dc_8af69e8081bf

How to cite

In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models — arXiv:2608.19514 — arXiv (en), https://arxiv.org/abs/2608.19514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8af69e8081bf (Metraipolis archive dc_8af69e8081bf, sha256 774d1c40257870ef266cadfb4ee91b753b2a8154aa41e0f6e95aa1e3615f2558)
BibTeX
@misc{dc8af69e8081bf,
  title = {In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models — arXiv:2608.19514},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19514},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8af69e8081bf; sha256 774d1c40257870ef266cadfb4ee91b753b2a8154aa41e0f6e95aa1e3615f2558},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Persistent intelligent systems require the ability to learn continually, but current machine learning approaches face significant challenges in this area compared to biological learning systems. Machine learning algorithms typically trade off retention of previously learned information and adaptation to new or changing data patterns. When continual learning capabilities are absent, algorithms must undergo retraining using the entire data set, an approach that becomes impractical when original training data are unavailable due to storage constraints, financial or computational costs, or privacy restrictions. However, biological animals can learn continually, without experiencing catastrophic forgetting. This paper attempts to build a high-level framework for how animals learn and preserve knowledge by modelling neural components and states that are known to be related to memory consolidation. We focus on three concepts: experience replay, REM sleep, and bilaterality. We propose 4MAS (4 Module Awake/Sleep), a novel macroarchitecture demonstrating how machine learning models might benefit from asymmetric hemispheres, each with their own long- and short-term memory mechanisms, and how a period of sleep between incremental learning tasks might benefit memory consolidation. Finally, we present results showing that our architecture achieves statistical improvements over established generative replay baselines on Split-MNIST (98.3%) and Split-Fashion-MNIST (84.9%), while reducing forgetting by more than half relative to the strongest replay baseline and demonstrating monotonic capacity scaling on Split-CIFAR-100 (29.29%).

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.19514 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T11:47:43.301Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).