AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

No One-Size-Fits-All Neurons: Task-Based Neurons for Artificial Neural Networks

Fenglei Fan, Meng Wang, Hangcheng Dong, Jianwei Ma, Tieyong Zeng

TPAMI 2026 · Architectures and efficiency › RNNs and normalization · approach: Mechanistic circuit interpretability · 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
use a task-based neuron learned by vectorized symbolic regression instead of a linear neuronfully connected network · synthetic p1 (S1)MSE: 0.0215 -> 0.0009Improved
use task-based neurons instead of linear neuronsfully connected network · fifa (S1)MSE: 0.0895 -> 0.0637Improved
use task-based neurons instead of linear neuronsfully connected network · phoneme (S2)accuracy: 0.8020 -> 0.8510Improved
replace a random polynomial neuron with a symbolic-regression-learned neuron (ablation)task-based network · vehicleaccuracy: 0.6894 -> 0.8176Improved
replace a random polynomial neuron with a symbolic-regression-learned neuron (ablation)task-based network · Bike Sharing DemandMSE: 0.0747 -> 0.0184Improved
replace a random polynomial neuron with a symbolic-regression-learned neuron (ablation)task-based network · creditaccuracy: 0.7427 -> 0.7441No clear effect
use VSR instead of conventional SR to fit low-dimensional tabular datasymbolic regression · concrete strengthMSE: 0.4617 -> 0.7914Hurt
build a neural network from the VSR neuron instead of using SR expression directlytask-based network · concrete strengthMSE: 0.4617 -> 0.1144Improved
use VSR instead of SR on high-dimensional synthetic datasymbolic regression · GMM synthetic D=400validation RMSE: 2775.011 -> 1273.311Improved
use Sigmoid instead of ReLU activation in task-based network (ablation)TN · Bike Sharing DemandMSE: 0.0189 -> 0.0110Improved
use Sigmoid instead of ReLU activation in linear network (ablation)LN · Bike Sharing DemandMSE: 0.0152 -> 0.0496Hurt
use a sine/cosine function space for the neuron instead of linear neurontask-based network · california housingMSE: 0.0564 -> 0.0512Improved

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