A dynamic architecture for artificial neural networks

Artificial neural networks (ANN), have shown to be an effective, general-purpose approach for pattern recognition, classification, clustering, and prediction. Traditional research in this area uses a network with a sequential iterative learning process based on the feed-forward, back-propagation algorithm. In this paper, we introduce a model that uses a different architecture compared to the traditional neural network, to capture and forecast nonlinear processes. This approach utilizes the entire observed data set simultaneously and collectively to estimate the parameters of the model. To assess the effectiveness of this method, we have applied it to a marketing data set and a standard benchmark from ANN literature (Wolf's sunspot activity data set). The results show that this approach performs well when compared with traditional models and established research.

[1]  C. Chatfield,et al.  Fourier Analysis of Time Series: An Introduction , 1977, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  David Mautner Himmelblau,et al.  Applied Nonlinear Programming , 1972 .

[3]  Xiru Zhang,et al.  Time series analysis and prediction by neural networks , 1994 .

[4]  F. S. Wong,et al.  Time series forecasting using backpropagation neural networks , 1991, Neurocomputing.

[5]  CottrellM.,et al.  Neural modeling for time series , 1995 .

[6]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[7]  Marie Cottrell,et al.  Neural modeling for time series: A statistical stepwise method for weight elimination , 1995, IEEE Trans. Neural Networks.

[8]  Paul A. Fishwick,et al.  Feedforward Neural Nets as Models for Time Series Forecasting , 1993, INFORMS J. Comput..

[9]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[10]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[11]  Ramesh Sharda,et al.  Neural Networks for the MS/OR Analyst: An Application Bibliography , 1994 .

[12]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[13]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[14]  Claas de Groot,et al.  Analysis of univariate time series with connectionist nets: A case study of two classical examples , 1991, Neurocomputing.

[15]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[16]  Marcus O'Connor,et al.  Artificial neural network models for forecasting and decision making , 1994 .

[17]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[18]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[19]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[20]  Suh Young Kang,et al.  An investigation of the use of feedforward neural networks for forecasting , 1992 .

[21]  D. E. Rumelhart,et al.  Learning internal representations by back-propagating errors , 1986 .

[22]  Geoffrey E. Hinton,et al.  Proceedings of the 1988 Connectionist Models Summer School , 1989 .

[23]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[24]  Shixin Cheng,et al.  Dynamic learning rate optimization of the backpropagation algorithm , 1995, IEEE Trans. Neural Networks.

[25]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[26]  BattitiRoberto.  First- and second-order methods for learning , 1992 .

[27]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[28]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.