Genetic Algorithm - Introduction

Genetic algorithms are search algorithms based on the mechanics of natural selection and natural genetics.

They efficiently exploit historical information or given information to speculate on new search points with expected improved performance.


Genetic Algorithms by Goldberg
Google with preview facility
http://books.google.co.in/books?id=6gzS07Sv9hoC

Tutorials on Genetic algorithm

http://www.ai-junkie.com/ga/intro/gat1.html

http://www.obitko.com/tutorials/genetic-algorithms/

Artificial Neural Networks - Wikibook Contents

Came across a wikibook on artificial neural network. I could not find the smooth navigation path. But found pages that have bits of information that I am looking for.

http://en.wikibooks.org/wiki/Artificial_Neural_Networks

http://en.wikibooks.org/wiki/Artificial_Neural_Networks/Neural_Network_Basics

This page has the explanation for the neuron under McCulloch-Pitts model

Xi is the dot product of input vector and a tap weight vector.

Output of the neuron is a function of Xi.

http://en.wikibooks.org/wiki/Artificial_Neural_Networks/History

Very brief history that covered McCulloch-Pitts model and backproparation algorithm.

Forecasting Exchange Rate in India: An Application of Artificial Neural Network Model

Forecasting Exchange Rate in India: An Application of Artificial Neural Network Model

Rudra P Pradhan, Rajesh Kumar

Abstract

The paper employs Artificial Neural Network (ANN) to forecast foreign exchange rate in India during 1992-2009. We used two types of data set (daily and monthly) for US dollar, British pound, euro and Japanese yen. The performance of forecasting is quantified by using various loss functions namely root mean square error (RMSE), mean absolute error (MAE), mean absolute deviation (MAD) and mean absolute percentage error (MAPE). Empirical results confirm that ANN is an effective tool to forecast the exchange rate. The technique gives the evidence that there is possibility of extracting information hidden in the foreign exchange rate and predicting it into the future. The evaluation of the proposed model is based on the estimation of the average behaviour of the above loss functions.

Keywords- Exchange Rate;  Neural Network

Full Text: PDF


This work is licensed under a Creative Commons Attribution 3.0 License.

Journal of Mathematics Research   ISSN 1916-9795(Print)   ISSN 1916-9809 (Online)
Copyright © Canadian Center of Science and Education