基于思维进化的MEBML算法的收敛性研究

A STUDY OF CONVERGENCE OF MIND EVOLUTION BASED MACHINE LEARNING

针对基于思维进化的机器学习 (MEBML )的马尔可夫链分析 ,证明了离散状态下趋同操作的群体依概率1收敛到全局最优状态 .但由于趋同操作的局部性 ,从局部最优状态转移到全局最优状态的概率非常小 .要增加这种转移概率 ,需要引进异化操作 .通过 P-最优状态和吸引域的概念 ,分析了趋同操作。

Based on the analysis of Markov chain on mind evolution based machine learning(MEBML),it is proved that the population generated by the similartaxis operation converges to the global optimum with probability 1 in discrete space.But because of the local property of the similartaxis operation, the transition probability from a local optimum to the global optimum is very small.To increase this transition probability,the dissimilation operation is introduced.Moreover,with the concepts of P optimal state and convergent region,theoretical and practical values of similartaxis and dissimilation operations are analyzed.