Constructive Neural Network Learning

doi:10.1109/TCYB.2017.2771463

Constructive Neural Network Learning

2019-01-01

20

OA

AI

DOI：10.1109/TCYB.2017.2771463

原文链接

查看原文

摘要

En 中文

In this paper, we aim at developing scalable neural network-type learning systems. Motivated by the idea of constructive neural networks in approximation theory, we focus on constructing rather than training feed-forward neural networks (FNNs) for learning, and propose a novel FNNs learning system called the constructive FNN (CFN). Theoretically, we prove that the proposed method not only overcomes the classical saturation problem for constructive FNN approximation, but also reaches the optimal learning rate when the regression function is smooth, while the state-of-the-art learning rates established for traditional FNNs are only near optimal (up to a logarithmic factor). A series of numerical simulations are provided to show the efficiency and feasibility of CFN.

Keyword:

Constructive neural network learning

generalization error

neural networks

saturation

Constructive Neural Network Learning

摘要

AI总结

期刊

机构