Research map / Architectures and efficiency / Spiking networks
SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural 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 |
|---|---|---|---|
| Use a binary heap and co-moving reference frame instead of scanning and evolving every neuron | Event-based simulation of sparse SNNs · Sparse SNN, fixed simulation time | computational cost scaling: O(N^2) -> O(K N log(N)) | Helped |
| Use a binary heap and co-moving reference frame instead of scanning and evolving every neuron | Event-based simulation of sparse SNNs · Sparse SNN, per network spike | computational cost scaling: O(N + K) -> O(K log(N)) | Helped |
| Use SparseProp rather than the conventional event-based algorithm | Sparse SNN simulation, 10^6 neurons · Sparse SNN simulation, 10^6 neurons, 100s | runtime: more then 3 CPU years -> less then one CPU hour | Helped |
| Apply SparseProp to a one-million-neuron sparse SNN | SparseProp · Sparse SNN simulation, 10^6 neurons | speedup: over four orders of magnitude | Helped |
Closest papers by meaning
- Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN (ICLR 2024 · similarity 0.92)
- Improving the Sparse Structure Learning of Spiking Neural Networks from the View of Compression Efficiency (ICLR 2025 · similarity 0.92)
- SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models (AAAI 2025 · similarity 0.90)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · similarity 0.89)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity (ICML 2025 · similarity 0.89)
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.