paper-with-me

홈 › Papers

AI Engram: In Search of Memory Traces in Artificial Intelligence

2026-06-12 · Jea Kwon, Dong-Kyum Kim, Jiwon Kim, Yonghyun Kim, Woong Kook, Meeyoung Cha arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.14997

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

From Artificial Intelligence to Brain Intelligence: The basis learning and memory algorithm for brain-like intelligence

2020-10-07 · Yifei Mao

The algorithm of brain learning and memory is still undetermined. The backpropagation algorithm of artificial neural networks was thought not suitable for brain cortex, and there is a lack of algorithm for memory engram.…

Hippocampusimage-classificationImage Classification

Engram Memory Encoding and Retrieval: A Neurocomputational Perspective

2025-06-02 · Daniel Szelogowski

Despite substantial research into the biological basis of memory, the precise mechanisms by which experiences are encoded, stored, and retrieved in the brain remain incompletely understood. A growing body of evidence sup…

Retrieval

Hebbian Memory-Augmented Recurrent Networks: Engram Neurons in Deep Learning

2025-07-29 · Daniel Szelogowski arxiv

Despite success across diverse tasks, current artificial recurrent network architectures rely primarily on implicit hidden-state memories, limiting their interpretability and ability to model long-range dependencies. In …

Stochastic Engrams for Efficient Continual Learning with Binarized Neural Networks

2025-03-27 · Isabelle Aguilar, Luis Fernando Herbozo Contreras, Omid Kavehei

The ability to learn continuously in artificial neural networks (ANNs) is often limited by catastrophic forgetting, a phenomenon in which new knowledge becomes dominant. By taking mechanisms of memory encoding in neurosc…

Computational EfficiencyContinual LearningGPU

EngramNCA: a Neural Cellular Automaton Model of Memory Transfer

2025-04-16 · Etienne Guichard, Felix Reimers, Mia Kvalsund, Mikkel Lepperød 외

This study introduces EngramNCA, a neural cellular automaton (NCA) that integrates both publicly visible states and private, cell-internal memory channels, drawing inspiration from emerging biological evidence suggesting…