网络群负相关训练算法的等价形式

在基于负相关的神经网络群学习算法中,相关项由目标输出或网络群输出定义。本文首先证明无论相关项采用何种定义形式,个体网络的目标函数都等价于网络自身性能和群性能的线性组合,线性组合系数由给定参数和网络群规模共同确定。然后给出个体网络目标函数的统一定义,并分析了目标函数内参数的含义。该目标函数表明负相关算法实际是实现多目标优化,所以网络群算法无需负相关概念,从而在概念和实现两方面简化了负相关算法。

An Equivalent Form of Negative Correlation Training Method of Ensemble Networks

In the negative correlation training method of ensemble networks,the correlation item is defined by means of the tar- get output or the ensemble output.We proved that the target function of an individual network is just a linear combination of its own per- formance and the ensemble performance,and the linear combination coefficients are determined by the prefixed parameter and the en- semble scale.With this proof,a unified target function is presented with clearly defined parameters.The target function reveals that the negative correlation method essentially belongs to multi-object optimization problems,and the concept of negative correlation is not nec- essary for the ensemble learning method,which results in a great simplification.