Over the past decade, ANN is used in many fields including Engineering and Medical electronics. ANN is also been applied to solve many problems of classification and prediction. Depending on the problem space and complexity various approaches were proposed to solve the problems in an efficient way. Multi-layer Feed forward network is one of the network architecture predominantly used to solve classification and prediction problems. The objective of this paper is to study the various methods available in the literature for solving those problems. The study starts with a simple feed forward network for image classification, then continued to investigate the methods to improve the classification accuracy using various wavelets and dimensionality reduction techniques. The various improvements were proposed for Backpropagation algorithm including complex BP were analysed. For performance improvement, methods of evolutionary algorithms and Pruning techniques were studied briefly. Finally the improved RBF network for complex numbers was analysed. This paper gives an overall idea of how the feed forward network was evolved with various approaches for solving classification and prediction problems.

Feed Forward, Classification, Predication, Backpropogration, PSO, RBF, Complex valued ANN.

[1] K. Verma, L. K. Verma and P. Tripathi, “Image Classification using Backpropogation Algorithm”, JOURNAL OF COMPUTER SCIENCE AND SOTWARE APPLICATION, Vol. 1, No.2, 2014
[2] T. Kathirvalavakumar, J. B. Vasanthi, “Face Recognition Based on Wavelet Packet Coefficients and Radial Basis Function”, Journal of Intelligent Learning Systems and Applications, 2013
[3] T. Kathirvalavakumar, J. B. Vasanthi, “Features Reduction using Wavelet and Discriminative Common Vector and Recognizing Faces using RBF”, International Journal of Computer Applications, Vol. 74, No.5, 2013
[4] Y. Xie and Y. Zhang, “A Wavelet Network Model for Short-Term Traffic Volume Forecasting”, Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, Vol. 10, No.3, pp.141-150, 2006
[5] A. Sinha, M. Pavithra and B. J. Pandian, “A Wavelet Neural Network based approach in Cancer Diagnosis and Biopsy Classification”, International Journal of Advancements in Research & Technology, Vol. 2, Issue.8, 2013
[6] M. Karthigaiselvi, T. Kathirvalavakumar, “Recognition of Words in Tamil Script Using Neural Network” , Int. Journal of Engineering Research and Application, Vol.7 Issue.3, (Part-6), pp.62-70, 2017
[7] S. K. Roy, C. F. Rodrigues, “Echo Canceller Using Error Back Propogration Algorithm”, International Conference on Soft Computing and Machine Intelligence, 2014
[8] G. A. Ali and A. Tayfour, “Characteristics and Prediction of Traffic Accident Casualties in Sudan Using Statistical Modelling and Artificial Neural Networks”, International Journal of Transportation Science and Technology, Vol.1 No.4.202, pp.305-317, 2012
[9] M. Sornam and P. Thangavel, “An improved three-term optical backpropogation algorithm”, Int. J. Artificial Intelligence and Soft Computing, Vol.2, No.4, pp.321-333, 2011
[10] D. Chhachhiya, A. Sharma and M. Gupta, “Designing optimal architecture of neural network with particle swarm optimization techniques specifically for educational dataset”, 7th International Conference on Cloud Computing, Data Science & Engineering, 2017
[11] T. He, T. Dan, Y. Wei, H. Li, X. Chen, G. Qin, “Particle Swarm Optimization RBF Neural Network Model for Internet Traffic Prediction”, International Conference on Intelligent Transportation, Big Data & Smart City, 2016
[12] X. Liu, X. Jiao, Y. Li and X. Liang, “Improved New Particle Swarm Algorithm Solving Job Shop Scheduling Optimization Problem”, 3rd International Conference on Computer Science and Network Technology, 2013
[13] M. G. Augasta, and T. Kathirvalavakumar, “Pruning algorithms of neural networks – a comparative study”, Cent. Eur. J. Comp Sci. Vol. 3(3), pp.105-115, 2003
[14] M. G. Augasta, and T. Kathirvalavakumar, “A Novel Pruning Algorithm for Optimizing Feedforward Neural Network of Classification Problems”, Springer, 2011
[15] T. Nitta, “A Back-propagation Algorithm for Complex Numbered Neural Networks”, Internal Joint Conference on Neural Networks, 1993
[16] H. E. Michel and A.A.S. Awwal, “Enhanced Artificial Neural Network using Complex Numbers”, IEEE, 1999
[17] A. S. Gangal, P.K. Kalra, and D.S. Chauhan, “Inversion of Complex Valued Neural Networks using Complex Back-propagation Algorithm”, International Journal of Mathematics and Computers in Simulation, Vol.3, Issue.3, 2009
[18] R. Savitha, S. Suresh and N. Sundararajan, “A Fully Complex-valued Radial Basis Function Network and its Learning Algorithm”, International Journal of Neural Systems, Vol.19 No.4, 99, pp.253-267, 2009
[19] R. Savitha, S. Suresh, N. Sundararajan andH. J. Kim, “A fully complex-valued radial basis function classifier for real-valued