Research map / Architectures and efficiency / Spiking networks
Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis
Yunduo Zhou, Bo Dong, Chang Li, Yuanchen Wang, Xuefeng Yin, Yang Wang, Xin Yang
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 DWAM to SAN | SAN · Obstacle avoidance, dynamic obstacle, LIF | success rate: 85.9% -> 90.1% | Improved |
| add DWAM to BDETT | BDETT · Obstacle avoidance, dynamic obstacle, SRM | success rate: 80.1% -> 87.3% | Improved |
| add DWAM to BDETT | BDETT · Obstacle avoidance, GN weight, LIF | success rate: 79.6% -> 89.8% | Improved |
| add DWAM to SAN | SAN · Obstacle avoidance, GN weight, LIF | success rate: 55.2% -> 70.4% | Improved |
| add DWAM to SAN | SAN · Obstacle avoidance, 8-bit Loihi weight, SRM | success rate: 85.5% -> 84.7% | Hurt |
| add DWAM to SAN | SAN · Obstacle avoidance, static obstacle | success rate: 97.5% -> 98.4% | No clear effect |
| add DWAM to SAN, lowering firing-rate change HM_m | SAN · Obstacle avoidance, GN weight, LIF | HM_m: 0.14374 -> 0.10598 | Improved |
| add DWAM to PopSAN | PopSAN · Ant-v3, GN weight, LIF | reward: 1324 -> 1519 | Improved |
| add DWAM to PopSAN | PopSAN · Ant-v3, GN observation, LIF | reward: 2160 -> 2541 | Improved |
| add DWAM to BDETT | BDETT · Ant-v3, GN weight, SRM | reward: 4939 -> 5558 | Improved |
| add DWAM to BDETT | BDETT · HalfCheetah-v3, GN observation, SRM | reward: 3701 -> 4037 | Improved |
| add DWAM to PopSAN | PopSAN · HalfCheetah-v3, MIN observation, LIF | reward: 9993 -> 10155 | No clear effect |
Closest papers by meaning
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.87)
- SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding (NeurIPS 2025 · similarity 0.86)
- FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor (NeurIPS 2024 · similarity 0.85)
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.85)
- Feedback control guides credit assignment in recurrent neural networks (NeurIPS 2024 · similarity 0.85)
- Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks (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.
