AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

One Neuron Saved is One Neuron Earned: On Parametric Efficiency of Quadratic Networks

Fenglei Fan, Hangcheng Dong, Zhongming Wu, Lecheng Ruan, Tieyong Zeng, Yiming Cui, Jing-Xiao Liao

TPAMI 2025 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 18 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
replace conventional neurons with quadratic neuronsone-hidden-layer network · Concentric hyperspheres (d=200)accuracy (%): 82.75 -> 100.00Improved
replace conventional neurons with quadratic neuronsone-hidden-layer network · Concentric hyperspheres (d=100)accuracy (%): 88.25 -> 100.00Improved
replace conventional neurons with quadratic neuronsone-hidden-layer network · Concentric hyperspheres (d=3)accuracy (%): 100.00 -> 100.00No clear effect
use quadratic network with fewer neuronsone-hidden-layer network · Gaussian mixture (20-dim)accuracy (%): 79.60 -> 82.00Improved
use quadratic network at matched parameter countone-hidden-layer network · Gaussian mixture (500-dim)accuracy (%): 66.60 -> 67.40Improved
add more neurons/depth to conventional network (ablation)conventional network · Gaussian mixture (20-dim)accuracy (%): 79.60 -> 79.20No clear effect
replace six layers in stage four of ResNet-50 with a 3-layer quadratic networkResNet-50 · ImageNet-1K valtop-1 accuracy (%): 75.3 -> 75.4No clear effect
use quadratic aggregation instead of widening (ablation)PointNet · S3DISmIOU: 45.2 -> 48.1Improved
use quadratic aggregation instead of stacking more layers (ablation)PointNet · S3DISmIOU: 46.1 -> 48.1Improved
use quadratic aggregation instead of linearDGCNN · S3DISmAcc: 57.0 -> 61.9Improved
use quadratic aggregation instead of widening (ablation)DGCNN · S3DISmIOU: 49.6 -> 50.6Improved
make DGCNN deeper (ablation)DGCNN · S3DISmIOU: 49.3 -> 49.9No 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