Forsgren, Anders and Kling, Robert, 2003

An implementation of recurrent neural networks for prediction and control of nonlinear dynamic systems
http://epubl.luth.se/1402-1617/2003/119/

Abstract

Neural networks have been used in identification and control of nonlinear dynamic systems for decades. Using recurrent neural networks which are themselves dynamic systems makes is possible to achieve models superior both to linear models and feedforward neural networks. Recurrent neural networks are able to capture the true hidden dynamics of nonlinear systems.

A software framework is developed which provides easy creation and training of arbitrary perceptron networks. An introduction to dynamic systems and system identification is given, as well as a short introduction to Kalman Filtering. The basics of neural networks in general and recurrent neural networks in particular are explained.

Recurrent multilayer perceptrons trained by the extended Kalman filter method are evaluated in a series of experiments. First, network structures are evaluated empirically by using them to identify and predict chaotic time series. Identification performance on both real world systems and simulated systems is compared to results obtained using linear models and feedforward neural networks. An identified model of a simulated nonlinear dynamic system demonstrates the use of a recurrent neural network in a predictive control scheme.

Kinzel, Wolfgang, 2000

Predicting and generating time series by neural networks: An investigation using statistical physics
http://citeseer.ist.psu.edu/378232.html

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.

Thank you so much for posting all of these great papers. I have just started my PhD in Algorithmic Trading, and have to say that my background is EEE .
I would like to make a great plan for myself, in order to know the starting point for my research, technique(NN's??), Maths,etc that I have to use on order to develop and a trading algo, from my set of high frequency data.
Appreciate any help and advice from you.
Mahnoosh