Entity · technique

Feedforward Neural Networks

techniqueactivefeedforward-neural-networks-29aaf0eb·1 events·first seen May 21, 2026

Aliases: Feedforward Neural Networks

Co-occurring entities

Universal Approximation Theorem depth-width trade-offs Sobolev Spaces Kolmogorov-Arnold Networks (KANs)

More like this (12)

Graph Neural Networks FeedForward submodule Recurrent Neural Network Spiking Neural Networks feed-forward transformer Reinforcement Learning from Human Feedback convolutional neural network neural network image classifiers large neural network training ResNet AlexNet Federated Learning

Recent events (1)

5arXiv · cs.AI·May 21, 2026·source ↗

Survey: Approximation Theory for Neural Networks — Classical Results and New Directions Including KANs

This arxiv survey reviews four decades of universal approximation theory for feedforward neural networks, covering classical density results for single-hidden-layer networks and quantitative bounds relating approximation error to network size and target function smoothness. It gives particular emphasis to depth-width trade-offs and the parameter efficiency advantages of deeper architectures for structured function classes. The survey also covers recent theoretical developments on Kolmogorov-Arnold Networks (KANs) as an alternative architectural paradigm with emerging approximation-theoretic analysis.

Evaluation and Benchmarking Feedforward Neural Networks Universal Approximation Theorem depth-width trade-offs +2 more