基于非联合型学习机制的学习神经元模型

摘要

针对生物神经细胞所具有的非联合型学习机制,设计了具有非联合型学习机制的新型神经元模型——学习神经元.首先,研究了非联合型学习机制中习惯化学习机制和去习惯化学习机制的简化描述;其次,建立了习惯化和去习惯化学习机制的数学模型;最后,基于经典的M-P (McCulloch-Pitts)神经元模型,提出了具有习惯化和去习惯化学习能力的新型神经元模型——学习神经元.经仿真实验验证,学习神经元具有典型的习惯化和去习惯化学习能力,为构建新型神经网络提供良好的基础.%Biological neurons have non-associative learning mechanisms,and a novel learning neuron with nonassociative learning mechanisms was designed,namely learning neuron.Firstly,the simplified description of the habituation learning mechanism and the dishabituation learning mechanism were researched in the non-associative learning mechanisms.Secondly,the mathematical models of habituation and dishabituation learning mechanisms were established.Finally,based on the classical M-P (McCulloch-Pitts) neuron model,the learning neuron model with the ability of habituation and dishabituation learning was proposed.The simulation results verify that the proposed learning neuron has typical habituation and dishabituation learning ability,and provides a good foundation for the construction of new neural network.