cd /news/machine-learning/in-two-minds-about-lifelong-learning… · home topics machine-learning article
[ARTICLE · art-105448] src=machinebrief.com ↗ pub= topic=machine-learning verified=true sentiment=· neutral

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

Researchers propose 4MAS (4 Module Awake/Sleep), a novel macroarchitecture that models asymmetric brain hemispheres with separate long- and short-term memory mechanisms and a sleep phase between tasks to improve continual learning. The architecture achieves 98.3% accuracy on Split-MNIST, 84.9% on Split-Fashion-MNIST, and 29.29% on Split-CIFAR-100, addressing catastrophic forgetting without retraining on full datasets.

read1 min views1 publishedAug 21, 2026

arXiv:2608.19514v1 Announce Type: new Abstract: 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 competitive results on the Split-MNIST, Split-Fashion-MNIST and Split-CIFAR-100 datasets, with 98.3%, 84.9%, and 29.29% accuracy respectively.

── more in #machine-learning 4 stories · sorted by recency
── more on @4mas 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/in-two-minds-about-l…] indexed:0 read:1min 2026-08-21 ·