paper-with-me

Papers

Measure theoretic results for approximation by neural networks with limited weights

2023-04-04 · Vugar Ismailov, Ekrem Savas

In this paper, we study approximation properties of single hidden layer neural networks with weights varying on finitely many directions and thresholds from an open interval. We obtain a necessary and at the same time sufficient measure theoretic condition for density of such networks in the space of continuous functions. Further, we prove a density result for neural networks with a specifically constructed activation function and a fixed number of neurons.

📄 PDF Abstract BibTeX arXiv:2304.01880

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Numerical Approximation Capacity of Neural Networks with Bounded Parameters: Do Limits Exist, and How Can They Be Measured?

2024-09-25 · Li Liu, Tengchao Yu, Heng Yong

The Universal Approximation Theorem posits that neural networks can theoretically possess unlimited approximation capacity with a suitable activation function and a freely chosen or trained set of parameters. However, a …

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

2020-08-19 · Ming Li, Sho Sonoda, Feilong Cao, Yu Guang Wang 외

We investigate the expressive power of depth-2 bandlimited random neural networks. A random net is a neural network where the hidden layer parameters are frozen with random assignment, and only the output layer parameter…

Learning Theory

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks

2020-02-24 · ICML 2020 1 · Agustinus Kristiadi, Matthias Hein, Philipp Hennig

The point estimates of ReLU classification networks---arguably the most widely used neural network architecture---have been shown to yield arbitrarily high confidence far away from the training data. This architecture, i…

Bayesian Inference

Random Neural Network Expressivity for Non-Linear Partial Differential Equations

2026-05-24 · Muhammed Ali Mehmood, Lukas Gonon arxiv

Neural networks with randomly generated hidden weights (RaNNs) have been extensively studied, both as a standalone learning method and as an initialization for fully trainable deep learning methods. In this work, we stud…

A Theoretical Understanding of Neural Network Compression from Sparse Linear Approximation

2022-06-11 · Wenjing Yang, Ganghua Wang, Jie Ding, Yuhong Yang

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly redu…

Model CompressionNeural Network Compression