AI Paper Atlas

Research map / Optimization / Optimizers

Gradient Descent for Spiking Neural Networks

Dongsung Huh, Terrence J. Sejnowski

NeurIPS 2018 · Optimization › Optimizers · approach: Constrained and non-backprop training · 36 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
Train a spiking network with the differentiable synapse model and exact gradient calculation30 NIF neurons · Auto-encoder taskoutput trackingImproved
Train a spiking network with the differentiable synapse model and exact gradient calculation30 NIF neurons · General predictive coding taskoutput trackingImproved
Train a spiking network with the differentiable synapse model and exact gradient calculation80 QIF neurons · Delayed-memory XOR tasktask performanceImproved
Use NIF neurons instead of QIF neurons (ablation)Spiking network trained on delayed-memory XOR · Delayed-memory XOR tasktask performanceHurt
Set regular recurrent weights W to zero (ablation)Spiking network trained on auto-encoding · Auto-encoder tasktask performanceNo clear effect
Use finite-time-constant fast synapses rather than instantaneously fast synapsesPredictive-coding spiking networks · Predictive coding tasksefficient codingNo clear effect
Use intrinsic QIF spiking nonlinearity without extra dendritic nonlinearitySpiking network trained on delayed-memory XOR · Delayed-memory XOR tasktask performanceImproved

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