Polynomial and standard higher order neural network

The generalized back propagation algorithm is extended to multi-layer higher-order neural networks (HONNs). The performance of HONNs is presented. Two basic structures, the standard form and the polynomial form, are discussed. The performance of these two structures is compared using the classical TC test case, the geometric rotation problem. Simulation results show that both types of constructing strategies can recognize noisy data under rotation up to 70% and noisy irrational data up to 94%. The effect of the number of hidden neurons is discussed.<<ETX>>

[1]  Hsin-Chia Fu,et al.  A variant of second-order multilayer perceptron and its application to function approximations , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[2]  Lilly Spirkovska,et al.  Coarse-coding applied to HONNs for PSRI object recognition , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[3]  L. Spirkovska,et al.  Rapid training of higher-order neural networks for invariant pattern recognition , 1989, International 1989 Joint Conference on Neural Networks.

[4]  C. Chang,et al.  Backpropagation algorithm in higher order neural network , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[5]  C. L. Giles,et al.  Machine learning using higher order correlation networks , 1986 .

[6]  Fernando J. Pineda,et al.  Generalization of Back propagation to Recurrent and Higher Order Neural Networks , 1987, NIPS.

[7]  Y. Okabe,et al.  Training the piecewise linear-high order neural network through error back propagation , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[8]  Clark C. Guest,et al.  High order neural networks with reduced numbers of interconnection weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[9]  C. L. Giles,et al.  Second-order recurrent neural networks for grammatical inference , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[10]  David Casasent.  Higher-order decision surfaces in neural nets , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[11]  High-order attention-shifting networks for relational structure matching , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[12]  Gerald Fahner,et al.  A higher order unit that performs arbitrary Boolean functions , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[13]  C. Lee Giles,et al.  Encoding Geometric Invariances in Higher-Order Neural Networks , 1987, NIPS.

[14]  Ja-Ling Wu,et al.  High-order perceptrons for decoding error-correcting codes , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[15]  C. L. Giles,et al.  High order correlation model for associative memory , 1987 .

[16]  J. F. Walkup,et al.  Reduction of interconnection weights in higher order associative memory networks , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[17]  Joydeep Ghosh,et al.  The pi-sigma network: an efficient higher-order neural network for pattern classification and function approximation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[18]  Georg Dorffner,et al.  A self-learning visual pattern explorer and recognizer using a higher order neural network , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[19]  Lilly Spirkovska,et al.  Connectivity strategies for higher-order neural networks applied to pattern recognition , 1990, 1990 IJCNN International Joint Conference on Neural Networks.