Research map / Architectures and efficiency / RNNs and normalization
Learning to play with spikes. Characterizing, predicting, and engineering unsupervised plasticity rules for spiking reservoir computing
Maciej Kania, Basile Confavreux, Tim Vogels
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Characterizes, predicts, and engineers unsupervised plasticity rules for spiking reservoir computing to improve reservoir performance over random initialization.
Problem
Spiking reservoir computing performance depends critically on reservoir initialization, and it is unclear which unsupervised plasticity rules best enrich fixed random reservoirs.
Approach
Characterizes and predicts which unsupervised plasticity rules benefit spiking reservoirs and uses this to engineer plasticity rules for reservoir computing; abstract is truncated so details are limited.
Closest papers by meaning
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.90)
- Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference (NeurIPS 2023 · similarity 0.90)
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks (NeurIPS 2026 · similarity 0.88)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.88)
- Discovering plasticity rules that organize and maintain neural circuits (NeurIPS 2024 · similarity 0.86)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 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.
