Research map / Label-efficient and robust learning / Recognition and long-tail
Noisy Adaptation Generates Lévy Flights in Attractor Neural Networks
Xingsi Dong, Tianhao Chu, Tiejun Huang, Zilong Ji, Si Wu
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 |
|---|---|---|---|
| add noise to spike frequency adaptation strength (gamma > 0) with mean strength near travelling-wave boundary | 2D CANN with SFA · bump movement in attractor space | step-size distribution (Brownian vs Levy) | Improved |
| decrease distance-to-boundary mu toward 0 | 2D CANN with noisy SFA · search efficiency in attractor space | search efficiency | Improved |
| increase mu beyond gamma^2/2 | 2D CANN with noisy SFA · bump movement | Levy exponent alpha: alpha >= 2 (Brownian motion) | Hurt |
| increase adaptation noise-to-strength ratio gamma | 2D CANN with noisy SFA, mu = 0.1 · bump movement | Levy exponent alpha | Improved |
Closest papers by meaning
- Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks (NeurIPS 2025 · similarity 0.85)
- Back to the Continuous Attractor (NeurIPS 2024 · similarity 0.84)
- Mechanistic Interpretability of RNNs emulating Hidden Markov Models (NeurIPS 2025 · similarity 0.84)
- Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics (NeurIPS 2024 · similarity 0.84)
- Dynamical phases of short-term memory mechanisms in RNNs (ICML 2025 · similarity 0.84)
- Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals (NeurIPS 2024 · similarity 0.83)
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.
