Abstract
In this paper, the memory capacity of Probabilistic Logic Neuron (PLN) network is discussed. We obtain two main results: (1) the method for constructing a PLN network with a given memory capacity; (2) the relationship between the memory capacity and the size of a PLN network. We show that the memory capacity of a PLN network depends on not only the number of input ports of its element but also the number of elements themselves. The results provide a new method for designing a PLN network.
Similar content being viewed by others
References
Bo Zhang, Ling Zhanget al., The Quantitative Analysis of the Behaviors of the PLN Network, Neural Network, vol.5, 1992, Pergamon Press, pp. 639–644.
Bo Zhang, Ling Zhanget al., The Complexity of Learning Algorithm in PLN Network, International Joint Conference on Neuron Network, Singapore, Nov. 1991.
I. Aleksander, The Logic of Connectional Systems, in Neural Computing Architecture, MA: MIT Press, 1989.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Zhang, B., Zhang, L. On memory capacity of the Probabilistic Logic Neuron network. J. of Compt. Sci. & Technol. 8, 252–256 (1993). https://doi.org/10.1007/BF02939532
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02939532