AI Engram: In Search of Memory Traces in Artificial Intelligence

• URL: http://arxiv.org/abs/2606.14997v1
• Date: Fri, 12 Jun 2026 22:36:52 GMT
• Title: AI Engram: In Search of Memory Traces in Artificial Intelligence
• Abstract summary: This work introduces a geometric framework to identify such "AI engrams"<n>We derive a closed-form estimator that isolates individual memory traces from globally entangled parameters.<n>Results bridge theories of biological memory and artificial representation learning.
• Score: 19.383960470953145
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning [22.364424301865856]
  We investigate when, where, and to what extent conditional memory should participate in scientific reasoning.<n>We propose a Knowledge Boundary-Aware Router that uses task-specific input proxies available before generation to determine whether memory is activated.<n>Our approach more consistently preserves beneficial memory contributions while suppressing memory-induced regressions.
  arXiv  Detail & Related papers  (2026-08-25T02:19:20Z)
• AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents [69.39123054975218]
  Memory serves as the pivotal nexus bridging past and future.<n>Recent research on autonomous agents has increasingly focused on designing efficient memory by drawing on cognitive neuroscience.
  arXiv  Detail & Related papers  (2025-12-29T10:01:32Z)
• MemGen: Weaving Generative Latent Memory for Self-Evolving Agents [57.1835920227202]
  We propose MemGen, a dynamic generative memory framework that equips agents with a human-esque cognitive faculty.<n>MemGen enables agents to recall and augment latent memory throughout reasoning, producing a tightly interwoven cycle of memory and cognition.
  arXiv  Detail & Related papers  (2025-09-29T12:33:13Z)
• Beyond Turing: Memory-Amortized Inference as a Foundation for Cognitive Computation [5.234742752529437]
  We introduce Memory-Amortized Inference (MAI) as a formal framework in which cognition is modeled as inference over latent cycles in memory.<n>We show that MAI provides a principled foundation for Mountcastle's Universal Cortical Algorithm.<n>We briefly discuss the profound implications of MAI for achieving artificial general intelligence.
  arXiv  Detail & Related papers  (2025-08-19T15:10:26Z)
• Engram Memory Encoding and Retrieval: A Neurocomputational Perspective [0.0]
  The engram theory posits that sparse populations of neurons undergo lasting physical and biochemical changes to support long-term memory.<n>This paper synthesizes insights from cellular neuroscience and computational modeling to address key challenges in engram research.<n>It suggests memory efficiency, capacity, and stability emerge from the interaction of plasticity and sparsity constraints.
  arXiv  Detail & Related papers  (2025-06-02T13:30:39Z)
• A Computational Model of Learning and Memory Using Structurally Dynamic Cellular Automata [0.0]
  This paper proposes a mathematical and computational model of learning and memory based on a small set of bio-plausible functions.<n> Experimental results show that the model can make near-optimal choices to re-discover a reward state after a single training run.
  arXiv  Detail & Related papers  (2024-12-20T17:26:17Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning [73.98142349171552]
  LOGICSEG is a holistic visual semantic that integrates neural inductive learning and logic reasoning with both rich data and symbolic knowledge. During fuzzy logic-based continuous relaxation, logical formulae are grounded onto data and neural computational graphs, hence enabling logic-induced network training. These designs together make LOGICSEG a general and compact neural-logic machine that is readily integrated into existing segmentation models.
  arXiv  Detail & Related papers  (2023-09-24T05:43:19Z)
• Unsupervised Learning of Invariance Transformations [105.54048699217668]
  We develop an algorithmic framework for finding approximate graph automorphisms. We discuss how this framework can be used to find approximate automorphisms in weighted graphs in general.
  arXiv  Detail & Related papers  (2023-07-24T17:03:28Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• Sequential Memory with Temporal Predictive Coding [6.228559238589584]
  We propose a PC-based model for emphsequential memory, called emphtemporal predictive coding (tPC) We show that our tPC models can memorize and retrieve sequential inputs accurately with a biologically plausible neural implementation.
  arXiv  Detail & Related papers  (2023-05-19T20:03:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.