Overview

Hopfield networks are recurrent systems that represent memories as stable states and recover them from incomplete or corrupted inputs. Classical binary models use Hebbian connections, while modern dense and kernel variants link retrieval to softmax attention; sparse, higher-order, asymmetric, and continuous-neuron designs aim to increase capacity. Researchers use statistical mechanics, random-matrix theory, and energy-landscape analysis to study storage, stability, and retrieval, alongside learning methods such as equilibrium propagation. Applications include image recognition, graph classification, protein generation, and memory editing, with a central tension between theoretical storage capacity and reliable retrieval under noise, interference, and changing data.

Latest papers

CardsList

45 papers7 papers in the last four weeks, up 133% on the four weeks before. 0.0% of all new papers.

  1. Neural networks and games

    Nov 3, 2026Philip R. NearyHopfield NetworksNash Equilibrium

  2. Memory flows: geometry and dynamics of sequential retrieval in input-driven Hopfield networks

    Nov 3, 2026Simone Betteti, Matteo Martin, Morten Gram Pedersen +2Hopfield NetworksAssociative Memory

  3. Phase Kernel Lifts Capacity of Dense Associative Memory

    Oct 15, 2026Yifei Zhao, Ying TangHopfield NetworksAssociative Memory

  4. On the Statistical Mechanics of Attention

    Oct 12, 2026Jerry Yao-Chieh Hu, Yu-An Chen, Maojiang Su +1Transformer AttentionAttention Mechanisms

  5. Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory

    Sep 15, 2026Yuto Sakurai, Takeaki Shimokawa, Kazunori Iwata +1Hopfield NetworksAssociative Memory

  6. Information Geometric Self-Organization at the Edge of Stability in High-Capacity Kernel Associative Memories

    Sep 15, 2026Akira TamamoriInformation GeometryEdge of Stability

  7. Geometry of learning dynamics: Gradient descent versus natural gradient on the ridge of optimization

    Sep 15, 2026Akira TamamoriInformation GeometryGradient Descent

  8. Hierarchical Prototype Emergence in Modern Hopfield Models

    Sep 10, 2026Aditya Cowsik, Adithya SriramNeural Network GeneralizationHopfield Networks

  9. Phases in a class of associative memories via hidden neurons

    Sep 10, 2026Toshihiro Ota, Masato TakiPhase TransitionsHopfield Networks

  10. Memory as an Energy Landscape---Hopfield

    Sep 2, 2026Nima DehghaniHopfield NetworksAssociative Memory

  11. Synthesis of Hopfield Neural Network: Novel Results

    Aug 26, 2026Garimella Rama MurthyHopfield NetworksDynamical Systems

  12. Basin-Preserving Discretizations of Modern Hopfield Retrieval Dynamics: Energy Cells, Dissipation, and the Attention Limit

    Aug 21, 2026Francisco R. VillatoroHopfield NetworksDynamical Systems

  13. High-Capacity Generalized Hopfield Networks

    Aug 8, 2026Victor GalitskiHopfield NetworksAssociative Memory

  14. New Synchronous Computation Dynamics for Hopfield Networks

    Jul 30, 2026Francisco Requena-Domínguez, Rafaela Benítez-Rochel, Ezequiel López-RubioNeural Network OptimizationHopfield Networks

  15. Free energy landscape of Dense Associative Memory

    Jul 21, 2026Sumedha, Abhishek SinghFree Energy CalculationNeural Network Memorization

  16. Robust Auto-associative Memory via Convolutional Restricted Hopfield Networks

    Jun 11, 2026Ci Lin, Tet Yeap, Iluju KiringaAdversarial RobustnessHopfield Networks

  17. Hyperbolic Neural Population Geometry Benefits Computation

    Jun 8, 2026Dennis Wu, Yi-Chun Hung, Braden Yuille +2Neural Representation GeometryNeural Processes

  18. Optimizing Energy-based Neural Network Training with Coherent Ising Machine

    Jun 8, 2026Chen-Rui Fan, Bo Lu, Zhi-Hong Zhang +3Equilibrium PropagationNeural Network Optimization

  19. Hybridizing Equilibrium Propagation with Ising Machines for Efficient Energy-Based Learning

    Jun 8, 2026Chen-Rui Fan, Bo Lu, Xing-Yu Wu +2Equilibrium PropagationHopfield Networks

  20. Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models

    May 27, 2026Ken Takeda, Masafumi Oizumi, Ryo KarakidaHopfield NetworksReplay-Based Continual Learning

  21. Beyond Fixed Points: Superpolynomial Capacity of Asymmetric Hopfield Networks

    May 23, 2026Aakash Kumar, Anatoly Khina, Frederik Mallmann-Trenn +1Dynamical SystemsHopfield Networks

  22. Efficient event-driven retrieval in high-capacity kernel Hopfield networks

    May 7, 2026Akira TamamoriHopfield NetworksNeuromorphic Computing

  23. HoReN: Normalized Hopfield Retrieval for Large-Scale Sequential Model Editing

    May 2, 2026Yuan Fang, Yi Xie, Xuming RanKnowledge EditingMemory-Augmented Language Models

  24. Geometric and dynamical analysis of attractor boundaries and storage limits in kernel Hopfield networks

    May 1, 2026Akira TamamoriDynamical SystemsNeural Representation Geometry

  25. Emergent Self-Attention from Astrocyte-Gated Associative Memory Dynamics

    Apr 28, 2026Arnau Vivet, Alex ArenasSoftmax AttentionDynamical Systems

  26. Learning Hippo: Multi-attractor Dynamics and Stability Effects in a Biologically Detailed CA3 Extension of Hopfield Networks

    Apr 22, 2026Daniele Corradetti, Renato CorradettiDynamical SystemsNeural Processes

  27. Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory

    Apr 22, 2026Akira TamamoriNeural Representation GeometryHopfield Networks