优化BP神经网络在手写体数字识别中的性能研究  

Research on performance optimization of BP neural network in handwritten numeral recognition

作　　者：王俊杰[1] 

机构地区：[1]北京工业大学,北京100124

出　　处：《电子设计工程》2017年第6期27-30,共4页Electronic Design Engineering

摘　　要：为了提高基于BP神经网络的手写体数字识别分类器的准确率与训练速度,针对基于BP神经网络的手写体数字识别分类器,从代价函数、权值初始化、正则方法消除过拟合几个方面对BP神经网络算法进行了改进。并使用MNIST数据集对分类器进行训练、验证、测试等实验。实验表明,改进后的手写体数字识别分类器的性能得到了优化。In order to improve the accuracy and training speed of handwritten numeral recognition classifier based on BP neural network,for handwritten numeral recognition classifier based on BP neural network,We improve the algorithm from the following aspects, such as cost function,initialization of weights, regularization method. And we use MNIST data set classifier to train, validate, and test. Experiments show that the handwritten digit recognition classifier improved performance has been optimized.

关 键 词：神经网络 BP算法 数字识别 分类器 

分 类 号：TN919.82[电子电信—通信与信息系统]