TY  - RPRT
VL  - 10.2139/ssrn.1667438
EP  - 38
A1  - Giovanis, Eleftherios
Y1  - 2010/08//
ID  - eprints1631
TI  - Applications of Feed-Forward Neural Networks with Error Backpropagation Algorithm and Non-Linear Methods in MATLAB
AV  - none
M1  - working_paper
N2  - In this paper we examine and present the methodology of feed-forward neural networks with error backpropagation algorithm and non-linear methods. We test some applications of time-series analysis in economics. The first part is consisted by applications following the traditional approach of neural networks. In the second part we propose a weighted input regression. Additionally, we present full programming routines in MATLAB in order to replicate the results and for further research applications, modifications, expansions and improvements. 
KW  - Keywords: Feed-Forward Neural Networks
KW  -  Error Backpropagation Algorithm
KW  -  Non-Linear Methods
KW  -  Time-Series
KW  -  Inflation Rate
KW  -  Treasury Bills
KW  -  Forecast
KW  -  MATLAB  -  JEL Classification: C22
KW  -  C45
KW  -  C53
KW  -  C63
KW  -  G10
UR  - http://ssrn.com/abstract=1667438
ER  -