However, many parameters as well as the training patterns are designed empirically in the original Neocognitron. 然而,在原始神经认知机中许多参数及训练模式都是凭经验设定的。
And then, the cooperative coevolution is incorporated to search reasonable parameters and training patterns for Neocognitron. 然后,结合协作进化为神经认知机搜索合理的参数和训练模式。