The emergence of neural network provide effective tools for a system with highly nonlinear input-output relations.
神经网络的出现为一类输入输出关系呈高度非线性的系统提供了建模的有效工具。
The results show that this algorithm can model input and output learning kernel of dynamic nonlinear system quickly, which is superior to other learning methods of wavelet network.
结果表明该算法能够对动态非线性系统的输入输出快速学习和建模，优于其它小波网络的学习算法。
Fuzzy Neural Network System (FNNS) can construct input? Output relationship by means of input and output signal and FNNS has special characteristics of adaptive learn while environment is changing.
模糊神经网络系统可以根据系统输入输出信号，建立系统的输入输出关系，并对环境的变化具有较强的自适应学习能力。
In addition, compared with high non-linear auditory system, artificial neural network has the capability to learn from limit sample sets and map input to output in various dimensions.
并且，对于高度非线性的听觉系统，采用从有限的实际样本中“自学习”到具有输入输出关系能力的人工神经网络模型来实现。
Then a neural network is employed to approximate the non-linear component of the input-output linearized system.
然后，针对输入—输出反馈线性化得到的数学模型中的非线性项，本文利用神经网络来对该部分进行逼近。
Then a neural network is employed to approximate the non-linear component of the input-output linearized system.
然后，针对输入—输出反馈线性化得到的数学模型中的非线性项，本文利用神经网络来对该部分进行逼近。
应用推荐