Feedforward Neural Network with Multi-valued Connection Weights

This paper introduces a new concept of the connection weight to the multi-layer feedforward neural network. The architecture of the proposed approach is the same as that of the original multi-layer feedforward neural network. However, the weight of each connection is multi-valued, depending on the value of the input data involved. The backpropagation learning algorithm was also modified to suit the proposed concept. This proposed model has been benchmarked against the original feedforward neural network and the radial basis function network. The results on six benchmark problems are very encouraging.

[1]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[2]  Silke Dodel,et al.  Analysis of correlated activity in fMRI data by artificial neural networks , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[3]  T. Selige,et al.  A Comparison of the Characterisation of Agricultural Land Using Singular Value Decomposition and Neural Networks , 1997 .

[4]  Raymond J. Mooney,et al.  Symbolic and Neural Learning Algorithms: An Experimental Comparison , 1991, Machine Learning.

[5]  H. Grip,et al.  Classification of neck movement patterns related to whiplash-associated disorders using neural networks , 2003, IEEE Transactions on Information Technology in Biomedicine.

[6]  Joseph M. Reinhardt,et al.  Mammographic masses classification: comparison between backpropagation neural network (BNN), K nearest neighbors (KNN), and human readers , 2003, CCECE 2003 - Canadian Conference on Electrical and Computer Engineering. Toward a Caring and Humane Technology (Cat. No.03CH37436).

[7]  B. Yegnanarayana,et al.  Incorporation of fuzzy classification properties into backpropagation learning algorithm , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[8]  Fabio Roli,et al.  Neurocomputation in Remote Sensing Data Analysis , 1997, Springer Berlin Heidelberg.

[9]  Ronald M. Welch,et al.  A neural network approach to cloud classification , 1990 .

[10]  Joseph M. Reinhardt,et al.  Classification of breast MRI lesions using a backpropagation neural network (BNN) , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[11]  Hagbae Kim,et al.  Multigradient: a new neural network learning algorithm for pattern classification , 2001, IEEE Trans. Geosci. Remote. Sens..

[12]  J. R. Quinlan,et al.  Comparing connectionist and symbolic learning methods , 1994, COLT 1994.

[13]  Jiawei Han,et al.  Data Mining: Concepts and Techniques , 2000 .

[14]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[15]  T. Martinez,et al.  Softprop: softmax neural network backpropagation learning , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).