Research map / Architectures and efficiency / RNNs and normalization
Dynamical properties of dense associative memory
Kazushi Mimura, Junichi Takeuchi, Yuto Sumikawa, Yoshiyuki Kabashima, Anthony CC Coolen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| include the retarded self-interaction term in the dynamics instead of neglecting it (ablation) | dense associative memory (n=3) · Dense associative memory n=3, parallel update | memory capacity | Improved |
| use higher-order interaction n>=3 instead of n=2 (traditional Hopfield) | associative memory · noise variance during retrieval | retrieval noise growth with overlap | Improved |
| increase interaction order n | dense associative memory · attraction basin | attraction basin size | No clear effect |
Closest papers by meaning
- Dense Associative Memory Through the Lens of Random Features (NeurIPS 2024 · similarity 0.93)
- Semantically-correlated memories in a dense associative model (ICML 2024 · similarity 0.90)
- On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis (ICML 2024 · similarity 0.89)
- Dense Associative Memory with Epanechnikov Energy (NeurIPS 2025 · similarity 0.88)
- Exponential Dynamic Energy Network for High Capacity Sequence Memory (NeurIPS 2025 · similarity 0.88)
- Factual recall in linear associative memories: sharp asymptotics and mechanistic insights (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
