Research map / Architectures and efficiency / RNNs and normalization
On Sparse Modern Hopfield Model
Jerry Yao-Chieh Hu, Donglin Yang, Dennis Wu, Chenwei Xu, Bo-Yu Chen, Han Liu
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 |
|---|---|---|---|
| Replace dense Hopfield pooling with sparse Hopfield pooling | Hopfield pooling · Bit pattern MIL, bag sizes 150, 200, and 300 | accuracy: 76.44 $\pm$ 0.23 -> 99.76 $\pm$ 0.00; 49.13 $\pm$ 0.01 -> 99.76 $\pm$ 0.00; 52.88 $\pm$ 0.01 -> 99.76 $\pm$ 0.00 | Improved |
| Replace dense Hopfield pooling with sparse Hopfield pooling | Hopfield pooling · Bit pattern MIL, bag sparsity 1%, 5%, and 40% | accuracy: 49.20 $\pm$ 0.00 -> 73.40 $\pm$ 0.06; 85.58 $\pm$ 0.10 -> 99.68 $\pm$ 0.00; 99.68 $\pm$ 0.00 -> 100.0 $\pm$ 0.00 | Improved |
| Replace dense Hopfield with sparse Hopfield | Hopfield MIL model · Tiger, Fox, Elephant, and UCSB breast cancer MIL | AUC: Tiger: $0.878\pm0.028$ -> $0.892\pm0.021$; Fox: $0.600\pm0.011$ -> $0.611\pm0.010$; Elephant: $0.907\pm0.022$ -> $0.912\ | Mixed |
Closest papers by meaning
- Nonparametric Modern Hopfield Models (ICML 2025 · similarity 0.93)
- On Computational Limits of Modern Hopfield Models: A Fine-Grained Complexity Analysis (ICML 2024 · similarity 0.92)
- Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models (ICML 2024 · similarity 0.92)
- Sparse and Structured Hopfield Networks (ICML 2024 · similarity 0.89)
- Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes (NeurIPS 2024 · similarity 0.87)
- In-Context Learning as Conditioned Associative Memory Retrieval (ICML 2025 · similarity 0.86)
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.
