Abstract
A multilayer neural network based on multi-valued neurons (MLMVN) is considered in the paper. A multi-valued neuron (MVN) is based on the principles of multiple-valued threshold logic over the field of the complex numbers. The most important properties of MVN are: the complex-valued weights, inputs and output coded by the kth roots of unity and the activation function, which maps the complex plane into the unit circle. MVN learning is reduced to the movement along the unit circle, it is based on a simple linear error correction rule and it does not require a derivative. It is shown that using a traditional architecture of multilayer feedforward neural network (MLF) and the high functionality of the MVN, it is possible to obtain a new powerful neural network. Its training does not require a derivative of the activation function and its functionality is higher than the functionality of MLF containing the same number of layers and neurons. These advantages of MLMVN are confirmed by testing using parity n, two spirals and “sonar” benchmarks and the Mackey–Glass time series prediction.
Similar content being viewed by others
References
Aizenberg I, Aizenberg N, Vandewalle J (2000) Multi-valued and universal binary neurons: theory, learning, applications. Kluwer, Boston
Aizenberg I, Bregin T, Butakoff C, Karnaukhov V, Merzlyakov N, Milukova O (2002) Type of blur and blur parameters identification using neural network and its application to image restoration. In: Dorronsoro JR (eds) Lecture notes in computer science, 2415. Springer, Berlin Heidelberg New York, pp 1231–1236
Aizenberg I, Myasnikova E, Samsonova M, Reinitz J (2002) Temporal classification of Drosophila segmentation gene expression patterns by the multi-valued neural recognition method. J Math Biosci 176(1):145–159
Aizenberg NN, Ivaskiv Yu L, Pospelov DA (1971) About one generalization of the threshold function (in Russian). The reports of the Academy of Sciences of the USSR. Doklady Akademii Nauk SSSR 196:1287–1290
Aizenberg NN, Ivaskiv Yu L (1977) Multiple-valued threshold logic (in Russian). Naukova Dumka, Kiev
Aizenberg NN, Aizenberg IN (1992) CNN based on multi-valued neuron as a model of associative memory for gray-scale images. In: Proceedings of the second IEEE International workshop on cellular neural networks and their applications, Technical University Munich, Germany, 14–16 October, 1992, pp 36–41
Aoki H, Kosugi Y (2000) An image storage system using complex-valued associative memory. In: Proceedings of the 15th international conference on pattern recognition, vol 2. IEEE Computer Society Press, pp 626–629
Aoki H, Watanabe E, Nagata A, Kosugi Y (2001) image association for endoscopic positional identification using complex-valued associative memories. In: Mira J, Prieto A (eds) Bio-inspired applications of connectionism. Lecture notes in computer science, 2085. Springer, Berlin Heidelberg New York, pp 369–374
Chen J-H, Chen C-S (2002) Fuzzy kernel perceptron. IEEE Trans Neural Netw 13:1364–1373
Cover TM (1965) Geometrical and statistical properties of systems of linear inequalities with application in pattern recognition. IEEE Trans Electron Comput 14:326–334
Fahlman JD, Lebiere C (1987) Predicting the Mackey–Glass time series. Phys Rev Lett 59:845–847
Franco L, Cannas SA (2001) Generalization properties of modular networks: implementing the parity function. IEEE Trans Neural Netw 12:1306–1313
Funahashi KI (1989) On the approximate realization of continuous mappings by neural networks. Neural Netw 2:183–192
Fung H, Li LK (2001) Minimal feedforward parity networks using threshold gates. Neural Comput 13:319–326
Georgiou GM, Koutsougeras C (1992) Complex domain backpropagation. IEEE Trans Circuits Syst CAS-II 39:330–334
Gorman RP, Sejnowski TJ (1988) Analysis of hidden units in a layered network trained to classify sonar targets. Neural Netw 1:75–89
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, Englewood Cliff
Hecht-Nielsen R (1988) Kolmogorov mapping neural network existence theorem. In: Proceedings of the 1st IEEE international conference on neural networks, vol 3. IEEE Computer Society Press, pp 11–13
Hecht-Nielsen R (1990) Neurocomputing. Addison Wesley, New York
Hirose A (ed) (2003) Complex valued neural networks. Theories and applications. World Scientific, Singapore
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward neural networks are universal approximators. Neural Netw 2:259–366
Impagliazzo R, Paturi R, Saks ME (1997) Size-depth tradeoffs for threshold circuits. SIAM J Comput 26:693–707
Islam MM, Yao X, Murase K (2003) A constructive algorithm for training cooperative neural networks ensembles. IEEE Trans Neural Netw 14:820–834
Jang J-SR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst, Man Cybern 23:665–685
Jankowski S, Lozowski A, Zurada JM (1996) Complex-valued multistate neural associative memory. IEEE Trans Neural Netw 7:1491–1496
Kim D, Kim C (1997) Forecasting time series with genetic fuzzy predictor ensemble. IEEE Trans Neural Netw 5:523–535
Kolmogorov AN (1957) On the representation of continuous functions of many variables by superposition of continuous functions and addition (in Russian). The Reports of the Academy of Sciences of the USSR. Doklady Akademii Nauk SSSR 114:953–956
Lee S-H, Kim I (1994) Time series analysis using fuzzy learning. In: Proceedings of the international conference on neural information processing, Seoul, Korea, vol 6, pp 1577–1582
Leung H, Haykin S (1991) The complex backpropagation algorithm. IEEE Trans Signal Process 39:2101–2104
Mackey MC, Glass L (1977) Oscillation and chaos in physiological control systems. Science 197:287–289
Mizutani E, Dreyfus SE, Jang J-SR (2000) On dynamic programming-like recursive gradient formula for alleviating hidden-node saturation in the parity problem. In: Proceedings of the international workshop on intelligent systems resolutions – the 8th Bellman continuum, Hsinchu, Taiwan, pp 100–104
Mizutani E, Dreyfus SE (2002) MLP’s hidden-node saturations and insensitivity to initial weights in two classification benchmark problems: parity and two-spirals. In: Proceedings of the 2002 international joint conference on neural networks (IJCNN’02), pp 2831–2836
Muezzinoglu MK, Guzelis C, Zurada JM (2003) A new design method for the complex-valued multistate hopfield associative memory. IEEE Trans Neural Netw 14:891–899
Müller K-R, Mika S, Rätsch G, Tsuda K, Shölkopf B (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12:181–201
Nitta T (1997) An extension of the backpropagation algorithm to complex numbers. Neural Netw 10:1391–1415
Paul S, Kumar S (2002) Subsethood-product fuzzy neural inference system (SuPFuNIS). IEEE Trans Neural Netw 13:578–599
Rumelhart DE, McClelland JL (1986) Parallel distributed processing: explorations in the microstructure of cognition. MIT Press, Cambridge
Russo M (2000) Genetic fuzzy learning. IEEE Trans Evol Comput 4:259–273
Siegelman H, Sontag E (1991) Neural nets are universal computing devices. Research Report SYCON-91–08. Rutgers Center for Systems and Control. Rutgers University
Vapnik V (1995) The nature of statistical learning theory. Springer, Berlin Heidelberg New York
Yao X, Liu Y (1997) A new evolutionary system for evolving artificial neural networks. IEEE Trans Neural Netw 8:694–713
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Aizenberg, I., Moraga, C. Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm. Soft Comput 11, 169–183 (2007). https://doi.org/10.1007/s00500-006-0075-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-006-0075-5