Hebbian Learning

Follow this topic Ask about this topic

Hebbian learning studies how connections change with correlated activity, providing a biologically inspired way to form representations and memories without relying entirely on backpropagation. Approaches include spike-timing-dependent plasticity, Oja-style rules, competitive and anti-Hebbian learning, fast weights, and associative-memory systems, sometimes combined with supervision, routing, replay, or consolidation. Researchers test these methods in settings such as image classification, few-shot learning on Omniglot, continual learning, and robot control, alongside theoretical work on stability, learning time, and memory capacity. A central tension is that local rules can support efficient adaptation and robust memory, but their accuracy, scalability, and resistance to interference often depend strongly on architecture, data, and how plasticity is controlled.

Latest papers

22 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Spatially-Aware Self-Organizing Graph Autoencoders via Localized Hebbian Learning
Oct 25, 2026Robin Koç, Hazal Moğultay Özcan, Fatoş T. Yarman VuralVisual Representation Learning Convolutional Autoencoder
Computer Engineering Department, Middle East Technical University, Ankara, Türkiye
Attention over noisy examples: generalization and memorization in the exponential Hopfield network
Oct 15, 2026Francesco AlemannoHopfield Networks Neural Network Memorization
A Geometry-Based Capacity Theory for Finite-Feature Associative Memory
Oct 6, 2026Jianhai Zhang, Donghao Zhang, Pattarawut Charatpangoon +4Associative Memory Information Retrieval
Department of Biomedical Engineering, Schulich School of Engineering, University of Calgary, and the Ron and Rene Ward Centre for Healthy Brain Aging Research, Hotchkiss Brain Institute, University of Calgary
Where Should Experience Live? Hierarchical Hebbian Memory for Continual Vision Transformers
Aug 31, 2026Mohammed Yusuf Mujawar, Noorbakhsh Amiri GolilarzHebbian Learning Vision Transformer
Department of Computer Science The University of Alabama, Tuscaloosa, AL, USA
Constrained Hebbian Learning Supports Efficient Representational Allocation under Structural Constraints
Jul 17, 2026Patrick Inoue, Florian Röhrbein, Andreas KnoblauchHebbian Learning Neural Encoding
KEIM Institute, Albstadt-Sigmaringen University, Germany · Department of Computer Science, Chemnitz University of Technology, Germany
Supervised Hebbian learning in Deep Counterstream Associative Networks
Jun 28, 2026Andreas KnoblauchHebbian Learning Associative Memory
Albstadt-Sigmaringen University, KEIM Institute, Poststrasse 6, 72458 Albstadt-Ebingen, Germany
Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning
Jun 23, 2026Mohammed Yusuf Mujawar, Noorbakhsh Amiri GolilarzHebbian Learning Vision Transformer
Department of Computer Science The University of Alabama, Tuscaloosa, AL, USA
Local Pheromone Network: Sparse Local Learning with Multi-Scale Synaptic Trails, Consolidation, and Replay
Jun 22, 2026Xingcheng Fu, Xianjun Chen, Zhihao LiHebbian Learning Continual Learning
Benchmarking local Hebbian learning rules for memory storage and prototype extraction
May 1, 2026Anders Lansner, Andreas Knoblauch, Naresh B Ravichandran +1Hebbian Learning Recurrent Neural Networks
1KTH Royal Institute of Technology, EECS, Stockholm · 2Stockholm University, Dept. of Mathematics, Stockholm · 3KEIM-Institute, Albstadt-Sigmaringen University, Germany +1
Where to Bind Matters: Hebbian Fast Weights in Vision Transformers for Few-Shot Character Recognition
Apr 22, 2026Gavin Money, Sindhuja Penchala, Jiacheng Li +1Hebbian Learning Vision Transformer
Department of Computer Science, The University of Alabama, Tuscaloosa, AL, USA
Incremental learning for audio classification with Hebbian Deep Neural Networks
Apr 20, 2026Riccardo Casciotti, Francesco De Santis, Alberto Antonietti +1Hebbian Learning Continual Learning
Signal Processing Research Centre, Tampere University, Tampere, Finland · Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Italy
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Apr 18, 2026Jinchang Zhu, Jindong Li, Cheng Zhang +2Memorization in Language Models Hebbian Learning
The Hong Kong University of Science and Technology (Guangzhou) · Jilin University · The Chinese University of Hong Kong
A Wasserstein Geometric Framework for Hebbian Plasticity
Apr 17, 2026Ulrich TanNeural Representation Geometry Hebbian Learning
Unsupervised Local Plasticity in a Multi-Frequency VisNet Hierarchy
Apr 9, 2026Mehdi Fatan Serj, C. Alejandro Parraga, Xavier OtazuVisual Representation Learning Hierarchical Representation Learning
Computer Vision Centre (CVC), Universitat Autonoma de Barcelona, Spain
Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents
Apr 4, 2026Diego Armando Resendez PradoNeuroevolution Hebbian Learning
Independent Researcher
Activity-Dependent Plasticity in Morphogenetically-Grown Recurrent Networks
Apr 3, 2026Sergii Medvid, Andrii Valenia, Mykola GlybovetsRecurrent Neural Networks Neuroevolution
National University of Kyiv-Mohyla Academy, Kyiv, Ukraine
Frame Theoretical Derivation of Three Factor Learning Rule for Oja's Subspace Rule
Apr 3, 2026Taiki YamadaHebbian Learning Principal Component Analysis
Hebbian Attractor Networks for Robot Locomotion
Mar 23, 2026Alexander Dittrich, Fuda van Diggelen, Dario FloreanoHebbian Learning Neural Network Training Dynamics
Laboratory of Intelligent Systems, EPFL, Switzerland
Scaling of learning time for high dimensional inputs
Mar 1, 2026Carlos Stein BritoNeural Network Training Dynamics Scaling Laws
NightCity Labs, Lisbon, Portugal
RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics
Feb 25, 2026Heng ZhangImage Classification Prototype-Based Classification
International Research Center for Neurointelligence (IRCN), University of Tokyo, Japan
Hebbian-Oscillatory Co-Learning
Feb 21, 2026Hasi HaysSparse Neural Networks Oscillatory Neural Networks
Department of Chemical Engineering, University of Arkansas, Fayetteville, AR 72701, USA
Building Supervision into Hebbian Plasticity through Spike Agreement
Jan 13, 2026Gouri Lakshmi S, Athira Chandrasekharan, Harshit Kumar +3Hebbian Learning Spiking Neural Networks
Indian Institute of Science Education and Research Thiruvananthapuram, Vithura, Thiruvananthapuram, Kerala 695551, India

Oct 25, 2026J/K move · Enter open · S save

Spatially-Aware Self-Organizing Graph Autoencoders via Localized Hebbian Learning

Robin Koç, Hazal Moğultay Özcan, Fatoş T. Yarman Vural

Computer Engineering Department, Middle East Technical University, Ankara, Türkiye

Visual Representation Learning Convolutional Autoencoder Graph Structure Learning Graph Neural Networks Hebbian Learning

Open paper AskPDF arXiv

Traditional autoencoders rely on static network architectures to learn latent representations. Recently we suggested a dynamic architecture inspired by Hebbian plasticity, enabling topological self-organization among convolutional feature maps (R. Koç et al., Proceedings of the SIU, 2026). Early implementations of this paradigm infer relationships among feature maps using global average pooling and model their interactions through scalar-valued connections. This approach falls short to fully exploit the underlying spatial information, embedded in input images. Furthermore, abrupt transitions between different loss functions and training dynamics can introduce representation shocks, leading to unstable feature learning. In this paper, we introduce a Spatially-Aware Self-Organizing Graph Autoencoder (S-LooM) to address these structural bottlenecks. By using spatial cross-correlation, and spatial kernels, S-LooM establishes dynamic connections among feature maps. We replace static scalar message passing of autoencoders with learnable spatial kernels and eliminate high-frequency deconvolutional artifacts observed in decoders using nearest-neighbor upsampling. Via a soft-blending training curriculum, the latent topology aligns smoothly during training. Our experiments show that S-LooM yields a more stable topology, compared to the state of the art dynamic architectures. Meaning, the graph structure that emerge has more resistance to feature entanglement and noise. It forms functional communities responsible for visual attributes, such as illumination, shape and texture even under high connection densities.