AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators

Yuhan Helena Liu, Stephen Smith, Stefan Mihalas, Eric Todd SheaBrown, Uygar Sümbül

NeurIPS 2022 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent dynamics models · 5 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
Add filtered modulatory credit propagation across recurrent stepsModProp · Pattern generationlearning performanceImproved
Add filtered modulatory credit propagation across recurrent stepsModProp · Delayed XORlearning performanceImproved
Add filtered modulatory credit propagation across recurrent stepsModProp · Sequential MNISTlearning performanceImproved
Use time-invariant filtered credit signals instead of precise spatiotemporal credit signalsModProp · Sequential MNISTlearning performance relative to BPTTHurt
Replace synapse-specific feedback weights with type-specific feedback weights (ablation)ModProp · Pattern generationlearning performanceNo clear effect
Replace synapse-specific feedback weights with type-specific feedback weights (ablation)ModProp · Delayed XORlearning performanceNo clear effect
Restore neuron-specific activation derivatives while retaining temporal averaging (ablation)ModProp_global · Pattern generationlearning performanceNo clear effect
Restore neuron-specific activation derivatives while retaining temporal averaging (ablation)ModProp_global · Delayed XORlearning performanceNo clear effect
Restore neuron-specific activation derivatives while retaining temporal averaging (ablation)ModProp_global · Sequential MNISTlearning performanceNo clear effect
Use fixed random type-specific modulatory weights instead of weights derived from synaptic weight averages (ablation)ModProp · Copy tasklearning performanceImproved
Increase the delayed XOR delay period to 1.5 times the original (ablation)ModProp with type-specific weights · Delayed XORlearning performanceHurt

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