论文部分内容阅读
以学习自动机为数学模型,结合斯金纳操作条件反射,建立一种人工感知运动系统,称为感知运动自动机(SMA).该系统包括感知状态集合、动作集合、感知运动取向性映射集合等9部分.系统引入好奇心和取向性概念,设计具有主动学习环境的内发动机机制,定义并分析了取向性学习过程,证明了系统熵的收敛性.通过模拟斯金纳鸽子实验表明了系统的可行性和有效性,仿真结果表明系统具有较好的自学习和自组织特性,同时稳定性较高.
Taking learning automata as a mathematical model and combining with Skinner’s operating condition reflection, an artificial perceived movement system (SMA) is built, which is composed of perceptual state set, action set and perceptual locomotor orientation map Etc. The system introduces the concept of curiosity and orientation, designs the internal engine mechanism with active learning environment, defines and analyzes the orientation learning process, and proves the convergence of system entropy.It shows that the system The simulation results show that the system has good self-learning and self-organizing characteristics and high stability.