摘要
基于匹配神经细胞突触、胞体和轴突的电神经生理特性,本文提出了一种接近真实神经细胞输入-输出关系和强度-时间曲线的,且具有非线性突触联接和适应性的非线性压控电阻电路模型,并分析了它的一些基本特性。结果表明,该模型比现存的神经网络更接近真实神经计算原理。由这一模型组成的胜者为王(WTA—Winner-Takes-All)网络能够比模拟网络更有效地检测出最大输出,并引入了强度竞争和时间竞争两个新概念。
Based on physiological properties of synapse, soma and axon, this paper presents and analyses a model of neural circuit which can approximately simulate input-output relation, strength-duration curve, adaption and nonlinear connection of real neuron. The obtained result; show that the model approximates to realistic principles of neural computation better than the available neural network. The impulse -coded WTA (Winner takes all) network constructed with the above model finds the winner more effectively than the analog WTA. Finally, the two important concepts: time competition and strength competition are introduced, which illustrate that the model has abilities to perform series and parallel information processing.
基金
国家自然科学基金
国防科学预研基金
关键词
人工神经元
突触联接
神经网络
Artificial neural net, Nonlinear connection, Adaption, Property ana- lysis, Competition