AI Paper Atlas

Research map / Optimization / Optimizers

A Differentiable Point Process with Its Application to Spiking Neural Networks

Hiroshi Kajino

ICML 2021 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
Replace the score function estimator with the path-wise estimatorSNN learning · Synthetic SNN gradient estimatesmean standard deviation: 2.49×10^3 -> 66.3Improved
Replace the score function estimator with the path-wise estimatorSNN learning · Synthetic SNN predictive performance, especially small training setsELBOImproved
Use the path-wise estimator, which generates more hidden spikesSNN learning · Synthetic SNN computational overheadcomputation time: 2.8 times more computation time than SNNHurt
Vary the concrete-distribution temperature within [0.1, 0.5] (ablation)∂SNN · Synthetic SNN predictive performanceperformanceNo clear effect
Share model and variational-distribution parameters by setting φ=θ (ablation)SNN variational learning · Synthetic SNN predictive performanceperformanceImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy