AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Global Credit Assignment via Dynamical Criticality

Wentao Wang, Keren Gao, Guozhang Chen

ICML 2026 · Architectures and efficiency › RNNs and normalization · approach: Hebbian and predictive coding

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 BPTT with COLA closed-form online rulevanilla tanh RNN · Addingtest MSE: 0.1426 -> 0.0059Improved
replace BPTT with COLAvanilla tanh RNN · Lorenz rolloutMSE: 0.6841 -> 0.0058Improved
replace BPTT with COLAvanilla tanh RNN · PTB-Charloss: 2.8695 -> 1.8352Improved
replace BPTT with COLAvanilla tanh RNN · Row-MNISTaccuracy: 0.9713 -> 0.9544Hurt
replace BPTT with COLAvanilla tanh RNN · UCI HARaccuracy: 0.8877 -> 0.8690Hurt
replace BPTT with COLARLIF spiking cell · N-MNISTaccuracy: 98.33% -> 98.54%Improved
replace BPTT with COLARadLIF spiking cell · N-MNISTaccuracy: 98.29% -> 93.56%Hurt
replace BPTT with COLAConvRNN · refinement and event-frame tasksaccuracyHurt
use two-point instead of scan-selected gain initialization (ablation)COLA · LorenzMSE: 0.0058 -> 0.0057No clear effect
use two-point instead of scan-selected gain initialization (ablation)COLA ConvRNN · Permuted MNISTaccuracy: 0.9136 -> 0.9230Improved
use near-critical initialization overheadCOLA · 11 benchmarksone-time overhead: 0.317% median (two-point)No clear effect

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