Predicting and generating time series by neural networks: An investigation using statistical physics
Disordered Systems and Neural Networks
2007-05-23 v1 Statistical Mechanics
q-bio
Abstract
An overview is given about the statistical physics of neural networks generating and analysing time series. Storage capacity, bit and sequence generation, prediction error, antipredictable sequences, interacting perceptrons and the application on the minority game are discussed. Finally, as a demonstration a perceptron predicts bit sequences produced by human beings.
Keywords
Cite
@article{arxiv.cond-mat/0010343,
title = {Predicting and generating time series by neural networks: An investigation using statistical physics},
author = {Wolfgang Kinzel},
journal= {arXiv preprint arXiv:cond-mat/0010343},
year = {2007}
}