A Learning Algorithm for Evolving Cascade Neural Networks
神经与进化计算
2007-05-23 v1 人工智能
摘要
A new learning algorithm for Evolving Cascade Neural Networks (ECNNs) is described. An ECNN starts to learn with one input node and then adding new inputs as well as new hidden neurons evolves it. The trained ECNN has a nearly minimal number of input and hidden neurons as well as connections. The algorithm was successfully applied to classify artifacts and normal segments in clinical electroencephalograms (EEGs). The EEG segments were visually labeled by EEG-viewer. The trained ECNN has correctly classified 96.69% of the testing segments. It is slightly better than a standard fully connected neural network.
引用
@article{arxiv.cs/0504055,
title = {A Learning Algorithm for Evolving Cascade Neural Networks},
author = {Vitaly Schetinin},
journal= {arXiv preprint arXiv:cs/0504055},
year = {2007}
}