Abstract
Auto-Associative neural networks have limited memory capacity and no classification capability. We propose a hetero-associative network consisting of a cumulative-learned forward 3-layer neural network and a backward 3-layer neural network, and a hetero-tandem associative network. The hetero-tandem associative network has a spindle type single cyclic-associative network with cumulative learning and is connected in tandem with the subsequent hetero-associative network. These hetero-associative networks with classification ability have high recognition performance as well as rapid attractor absorption.
Consecutive codification of outputs in the forward network was found to produce no spurious attractors, and coarse codification of converged attractors can be easily identified as training or spurious attractors.
Cumulative learning with prototypes and additive training data adjacent to prototypes can also drastically improve associative performance of both the spindle type single cyclic- and hetero-associative networks, allowing them to effectively be connected in tandem.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
8 References
Hassoun, M. H. (1993) Dynamic Associative Neural Memories. In: Hassoun, M. H. (eds.) Associative Neural Memories, Theory and Implementation 1993. Oxford University Press, pp.3–27.
Yingquan Wu and Stella N. Batalama. (2001) Improved One-Shot Learning for Feedforward Associative Memories with Application to Composite Pattern Association. IEEE Trans. on Systems, Man, and Cybernetics-Part B: Cybernetics, 31,1:119–125.
Amari, S. Yanai, H. (1993) Statistical Neurodynamics of Various Types of Associative Nets. In: Hassoun, M. H. (eds.) Associative Neural Memories, Theory and Implementation 1993. Oxford University Press, pp. 169–183.
deCallatay, A. M. (1986) Natural and Artificial Intelligence Processor Systems Compared to the Human Brain 1986. Elservier Science Publishers B. V.
Yatsuzuka, Y., Enomoto, M. (1996) A Binary Three Layer neural Network with Switched Error Perturbation and Reiterative Learning Utilizing the Generalization Property. ANNIE’96, 6:35–44.
Yatsuzuka, Y., Sugiyama, T. (2002) Parallel Neural Networks by Actively Repetitive Learning with Autonomous Label Assignment and Majority Voting. Proc. of the First International AISO Congress on Autonomous Intelligent Systems, 10028-02-YY-111.
Amari, S. and Maginu, K., (1988) Statistical neurodynamics of associative memory. Neural Networks, 1:63–73.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag/Wien
About this paper
Cite this paper
Yatsuzuka, Y., Ho, Y. (2005). Large Scale Hetero-Associative Networks with Very High Classification Ability and Attractor Discrimination Consisting of Cumulative-Learned 3-Layer Neural Networks. In: Ribeiro, B., Albrecht, R.F., Dobnikar, A., Pearson, D.W., Steele, N.C. (eds) Adaptive and Natural Computing Algorithms. Springer, Vienna. https://doi.org/10.1007/3-211-27389-1_21
Download citation
DOI: https://doi.org/10.1007/3-211-27389-1_21
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-24934-5
Online ISBN: 978-3-211-27389-0
eBook Packages: Computer ScienceComputer Science (R0)