基于发现蚁群算法优化神经网络是利用蚁群算法在解空间寻找出一组最优的权值和阈值，然后将这一组解带回到神经网络进行细致优化，从而得到最好的权值和阈值。(Found that the ant colony algorithm to optimize the neural network based on Ant Colony Algorithm in the solution space to find a set of optimal weights and threshold based on, and then the group returned to the neural network with detailed optimization, the best weight and threshold to get. But this does not fundamentally solve the disadvantage that the BP algorithm is easy to fall into the local minimum, because he hat algorithm will ensure that he gets the best result? In particular, the prediction is not t)