Research map / Probabilistic and scientific modeling / Dynamical systems
Online Learning Of Neural Computations From Sparse Temporal Feedback
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 |
|---|---|---|---|
| Remove the event-dependent scaling (EDS) factor (vanilla update rule) (ablation) | EDS learning rule · LIF and LRF parameter recovery | training success | Hurt |
| Learn only synaptic weights, freezing intrinsic parameters (ablation) | EDS learning rule · LIF neuron teacher-student | direct hit spikes: 18.5% -> 94% | Hurt |
| Learn only synaptic weights, freezing intrinsic parameters (ablation) | EDS learning rule · LRF neuron teacher-student | direct hit spikes: 12.9% -> 96.3% | Hurt |
| Use vanilla rule without EDS on single LIF parameters (ablation) | vanilla rule · LIF neuron | parameter recovery | No clear effect |
| Use vanilla rule without EDS on parameter combinations (ablation) | vanilla rule · LIF neuron | parameter recovery | Hurt |
| Replace EDS with SuperSpike surrogate gradient (ablation) | EDS learning rule · LIF neuron | parameter recovery | Hurt |
| Make surrogate gradient more similar to vanilla by changing beta, synaptic weights only (ablation) | SuperSpike surrogate · LIF neuron | recovery rate | Helped |
| Replace EDS with surrogate gradient (ablation) | EDS learning rule · LRF neuron | parameter recovery | Hurt |
| Add EDS factor to expected parameter update for correlated spike trains (ablation) | vanilla rule · Poisson spike train analysis of Vr update | update direction | Helped |
| Add Gaussian temporal noise to target spike times | EDS learning rule · LIF and LRF neurons | precision of solution | Hurt |
| Highest temporal noise level (sigma 3) for LRF with target rate above 35Hz | EDS learning rule · LRF neuron | convergence | Hurt |
| Increase target firing rate | EDS learning rule · LIF and LRF neurons | convergence time | Helped |
Closest papers by meaning
- Impression learning: Online representation learning with synaptic plasticity (NeurIPS 2021 · similarity 0.88)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Feedback control guides credit assignment in recurrent neural networks (NeurIPS 2024 · similarity 0.87)
- Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks (NeurIPS 2025 · similarity 0.86)
- Model Based Inference of Synaptic Plasticity Rules (NeurIPS 2024 · similarity 0.85)
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.