AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Push-pull Feedback Implements Hierarchical Information Retrieval Efficiently

Xiao Liu, Xiaolong Zou, Zilong Ji, Gengshuo Tian, Yuanyuan Mi, Tiejun Huang, K. Y. Michael Wong, Si Wu

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired network comparison · 0 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 sequential push then pull feedback between layerstwo-layer hierarchical Hopfield-type network · VGG-derived cat/dog image memory patterns, 1800 imageslayer-1 retrieval accuracy: 71.04%Improved
apply push (positive) feedback early (ablation)two-layer hierarchical network · cat/dog image patternsretrieval accuracy of cousin (other-category) patternsImproved
apply pull (negative) feedback later (ablation)two-layer hierarchical network · cat/dog image patternsretrieval accuracy of target child patternImproved
add pull feedback W = -b1 delta to subtract part of the parent mean (ablation)two-layer hierarchical network · synthetic hierarchical patterns, N=2000intra-class noise tail causing retrieval errorsImproved
use discrete instead of continuous Hopfield dynamics (ablation)push-pull feedback · synthetic hierarchical patternsoverall joint effect of push-pullHurt

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