Jianyong Chen et cl had proposed that initializing the connection weights and thresholds of BP neural network with chaotic values can improve the success rate of learning,and given the XOR problem as an example.
Jianyong chen等人提出以混沌序列初始化BP神经网络的连接权重及阈值有助于提高网络的学习成功率,并以对异或问题的学习作为例证。
参考来源 - BP神经网络初始化问题探讨·2,447,543篇论文数据，部分数据来源于NoteExpress
At last, a kind of BP algorithm with adaptive learning rate is evaluated and compared with standard BP algorithm by XOR problem.
最后结合XOR问题把一种自适应学习率BP算法和标准BP算法进行了比较和评价。
The algorithm is applied to XOR problem and nonlinear function approximation. Simulation results show that the chaos-BP algorithm needs shorter learning time than that of the standard BP and fast BP.
采用混合算法对XOR问题和非线性函数进行仿真，结果表明该算法明显优于标准BP算法和快速BP算法。
应用推荐