Research map / Architectures and efficiency / RNNs and normalization
Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks
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 |
|---|---|---|---|
| Increase neurons per site from 4 to 100 (ablation) | Structured similarity matching · MNIST test | classification error (%): 3.87 -> 1.40 | Helped |
| Increase neurons per site from 64 to 100 (ablation) | Structured similarity matching · MNIST test | classification error (%): 1.47 -> 1.40 | Helped |
| Use NPS 100 instead of the biologically plausible training baseline | MNIST classification · MNIST | classification error (%): 1.46% -> 1.40 | Helped |
Closest papers by meaning
- H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks (NeurIPS 2020 · similarity 0.87)
- Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs (ICLR 2023 · similarity 0.87)
- Two Tales of Single-Phase Contrastive Hebbian Learning (ICML 2024 · similarity 0.87)
- Credit Assignment in Neural Networks through Deep Feedback Control (NeurIPS 2021 · similarity 0.87)
- Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning (NeurIPS 2025 · similarity 0.86)
- Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks (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.