On Memory Capacity of the Probabilistic Logic Neuron Network

• 作 者: 张钹 张铃
• 机 构: Dept.of Computer Science and Technology Tsinghua University,Beijing 100084,Dept.of Mathematics,Anqin
• 出 处: Journal of Computer Science and Technology
• 发表日期: 1993年03期
• 关键词: Neuron constructing themselves discussion layered intend questions designing Por

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 memorycapacity;(2)the relationship between the memory capacity and the size of a PLN network.We showthat the memory capacity of a PLN network depends on not only the number of input ports of itselement but also the number of elements themselves.The results provide a new method for designing aPLN network.

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 memorycapacity; (2) the relationship between the memory capacity and the size of a PLN network.We showthat the memory capacity of a PLN network depends on not only the number of input ports of itselement but also the number of elements. The results provide a new method for designing aPLN network.