{"slug": "ai-engram-in-search-of-memory-traces-in-artificial-intelligence", "title": "AI Engram: In Search of Memory Traces in Artificial Intelligence", "summary": "Researchers introduced a geometric framework to identify 'AI engrams'—identifiable memory traces in deep neural networks analogous to biological memory units. The method enables surgical manipulation of learned knowledge through linear arithmetic, demonstrated from simple MLPs to large language models, bridging biological memory theory and artificial representation learning.", "body_md": "arXiv:2606.14997v1 Announce Type: new\nAbstract: Memory formation is fundamental to intelligence, yet whether deep neural networks preserve identifiable memory traces analogous to biological memory units remains an open question. This work introduces a geometric framework to identify such \"AI engrams\" by formalizing the neuroscientific criteria of specificity, reactivation, sufficiency, and necessity into a constrained inverse problem. We derive a closed-form estimator that isolates individual memory traces from globally entangled parameters, and show that this biologically-derived solution corresponds to a natural gradient update on the parameter manifold. AI engrams enable surgical manipulation of learned knowledge: any subset of memories can be composed or erased through linear arithmetic, without iterative optimization. Experiments ranging from simple MLPs to LLMs demonstrate the causal validity and substantial scalability of AI engrams. Together, these results bridge theories of biological memory and artificial representation learning and offer geometric insight into how deep networks simultaneously support functional specificity within distributed storage.", "url": "https://wpnews.pro/news/ai-engram-in-search-of-memory-traces-in-artificial-intelligence", "canonical_source": "https://arxiv.org/abs/2606.14997", "published_at": "2026-06-16 04:00:00+00:00", "updated_at": "2026-06-16 04:20:35.393579+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "neural-networks", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/ai-engram-in-search-of-memory-traces-in-artificial-intelligence", "markdown": "https://wpnews.pro/news/ai-engram-in-search-of-memory-traces-in-artificial-intelligence.md", "text": "https://wpnews.pro/news/ai-engram-in-search-of-memory-traces-in-artificial-intelligence.txt", "jsonld": "https://wpnews.pro/news/ai-engram-in-search-of-memory-traces-in-artificial-intelligence.jsonld"}}