Research map / Optimization / Optimizers
A Differentiable Point Process with Its Application to Spiking Neural Networks
Hiroshi Kajino
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 |
|---|---|---|---|
| Replace the score function estimator with the path-wise estimator | SNN learning · Synthetic SNN gradient estimates | mean standard deviation: 2.49×10^3 -> 66.3 | Improved |
| Replace the score function estimator with the path-wise estimator | SNN learning · Synthetic SNN predictive performance, especially small training sets | ELBO | Improved |
| Use the path-wise estimator, which generates more hidden spikes | SNN learning · Synthetic SNN computational overhead | computation time: 2.8 times more computation time than SNN | Hurt |
| Vary the concrete-distribution temperature within [0.1, 0.5] (ablation) | ∂SNN · Synthetic SNN predictive performance | performance | No clear effect |
| Share model and variational-distribution parameters by setting φ=θ (ablation) | SNN variational learning · Synthetic SNN predictive performance | performance | Improved |
Closest papers by meaning
- Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals (NeurIPS 2024 · similarity 0.88)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · similarity 0.87)
- Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network (ICML 2024 · similarity 0.86)
- Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks (NeurIPS 2024 · similarity 0.86)
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.86)
- Inferring stochastic low-rank recurrent neural networks from neural data (NeurIPS 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.
