Research map / Continual learning / Online and replay-based
Multi-Synaptic Cooperation: A Bio-Inspired Framework for Robust and Scalable Continual Learning
Penghui Li, Zhuang Ma, Yunliang Zang, Qiang Yu
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 multi-synaptic connectivity (ablation) | MSCN (ANN) · PMNIST | ACC (%): 96.79 -> 97.53 | Improved |
| add multi-synaptic connectivity (ablation) | MSCN (ANN) · 10-split CIFAR-100 | ACC (%): 77.03 -> 77.37 | Improved |
| add multi-synaptic connectivity (ablation) | MSCN (ANN) · TinyImageNet | ACC (%): 73.81 -> 75.03 | Improved |
| add multi-synaptic connectivity (ablation) | MSCN (ANN) · 5-Datasets | ACC (%): 93.47 -> 93.69 | Improved |
| add eligibility-trace plasticity modulation (ablation) | MSCN (ANN) · PMNIST | ACC (%): 96.53 -> 97.53 | Improved |
| add eligibility-trace plasticity modulation (ablation) | MSCN (ANN) · 10-split CIFAR-100 | ACC (%): 76.81 -> 77.37 | Improved |
| add eligibility-trace plasticity modulation (ablation) | MSCN (ANN) · TinyImageNet | ACC (%): 73.78 -> 75.03 | Improved |
| add eligibility-trace plasticity modulation (ablation) | MSCN (ANN) · 5-Datasets | ACC (%): 93.51 -> 93.69 | Improved |
| add MSCN to EWC | EWC · 10-split CIFAR-100 | ACC (%): 72.77 -> 73.26 | Improved |
| add MSCN to ER | ER · 10-split CIFAR-100 | ACC (%): 70.07 -> 71.13 | Improved |
| add MSCN to Bayesian | Bayesian · 10-split CIFAR-100 | ACC (%): 75.57 -> 76.48 | Improved |
| add MSCN to ER | ER · TinyImageNet | BWT (%): -19.86 -> -9.17 | Improved |
Closest papers by meaning
- Continual Learning Through Synaptic Intelligence (ICML 2017 · similarity 0.91)
- Continual Reinforcement Learning with Complex Synapses (ICML 2018 · similarity 0.90)
- SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding (NeurIPS 2025 · similarity 0.88)
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.88)
- Discovering plasticity rules that organize and maintain neural circuits (NeurIPS 2024 · similarity 0.86)
- Efficient Spiking Neural Networks with Sparse Selective Activation for Continual Learning (AAAI 2024 · 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.
