Research map / Architectures and efficiency / RNNs and normalization
Hopfield Networks is All You Need
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use HopfieldPooling instead of the strongest reported baseline | MIL classification · Tiger | AUC: 91.0±1.0 -> 91.3±0.5 | Helped |
| Use HopfieldPooling instead of the strongest reported baseline | MIL classification · Fox | AUC: 73.8±1.6 -> 64.05±0.4 | Hurt |
| Use HopfieldPooling instead of the strongest reported baseline | MIL classification · Elephant | AUC: 94.4±0.7 -> 94.9±0.3 | Helped |
| Use HopfieldPooling instead of the strongest reported baseline | MIL classification · UCSB Breast Cancer | AUC: 88.0±2.2 -> 89.5±0.8 | Helped |
| Use DeepRC with HopfieldPooling instead of the strongest reported baseline | Immune repertoire classification · Real-world dataset | AUC: 0.825±0.022 -> 0.832±0.022 | Helped |
| Use HopfieldLayer rather than SVM | UCI small-dataset classification · 75 small UCI datasets | Average rank difference: -3.23 -> -3.92 | No clear effect |
| Use HopfieldLayer with the training data as stored patterns | Drug-design prediction · SIDER | Score | Helped |
| Use HopfieldLayer with the training data as stored patterns | Drug-design prediction · BACE | Score | Helped |
Closest papers by meaning
- Sparse and Structured Hopfield Networks (ICML 2024 · similarity 0.89)
- On the Role of Hidden States of Modern Hopfield Network in Transformer (NeurIPS 2025 · similarity 0.88)
- Nonparametric Modern Hopfield Models (ICML 2025 · similarity 0.86)
- Rectified Lagrangian for Out-of-Distribution Detection in Modern Hopfield Networks (AAAI 2025 · similarity 0.86)
- Continual Learning in Modern Hopfield Networks with an Application to Diffusion Models (NeurIPS 2026 · similarity 0.85)
- Outlier-Efficient Hopfield Layers for Large Transformer-Based Models (ICML 2024 · similarity 0.85)
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.