从激励函数、权值修正方法、目标函数三方面对多个改进算法进行收敛性能的比较。
The convergence performances of many algorithms are compared from three aspects: activation function, weight modification methods, and target function.
根据实际产出需求，采用鲁棒消费策略，修正产出同时使消费过程中的目标函数达到最优。
According to the output demand and by using the Robust consumption strategy, the output is revised and a target function of consumption process is optimal.
选择adpcm的步长修正因子M涉及复杂目标函数的多变量优化，是一个海量计算问题。
Choice of ADPCM's step-size updating factors m had a sea capacity of computing which optimizes multi-variables with complex cost function.
应用推荐