atlas

Research map / Architectures and efficiency / RNNs and normalization

Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

NeurIPS 2020 · Architectures and efficiency › RNNs and normalization · approach: Backprop-free credit assignment · 58 citations (OpenAlex)

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 changedWhereMeasuredEffect
use Z-IL instead of IL for weight updatespredictive coding network · ImageNetruntime per weight update, GPU (ms): 56.3 -> 4.1Helped
add the phi function for full autonomy (Fa-Z-IL vs Z-IL)Z-IL · ImageNetruntime per weight update, GPU (ms): 4.1 -> 4.2No clear effect
increase detection window td from 1 to 4 (ablation)Fa-Z-IL phi · Inference-moment detectionsuccess rate: 93.4% -> 100.0%Helped
add C1 (initialize value nodes at prediction equilibrium, sigma=0) (ablation)Z-IL · MNISTdivergence from BP (test error, final weights)Helped
add C2 (update weights at t=l instead of fixed tc) (ablation)Z-IL · MNISTdivergence from BP (test error, final weights)Helped
add C3 (integration step gamma=1) (ablation)Z-IL · MNISTdivergence from BP (test error, final weights)Helped

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