基于bp网络分类和hopfield网络联想分类能力的分析-应用数学专业论文.docxVIP

中北大学学位论文 中北大学学位论文 Abstract This paper mainly studies the two typical artificial neural networks in the artificial neural network--BP network and Hopfield network. We deeply study the Classification and recognition of the two networks, and compare the advantages and disadvantages of the two networks. Then we improve the recognition of BP network in handwriting. And to study the characteristics of handwritten image extraction, we test its effect by BP network, and the test results are satisfied. Neural network can be used in pattern recognition. This function has great utility value. This paper studies the recognition ability of BP network and the discrete Hopfield neural network. It compares the identification ability of BP network and discrete Hopfield network in numbers, letters, handwritten digit, receiving the considerable conclusion that the noise in a certain range, the recognition effect of discrete Hopfield neural network is better; when the noise exceeds this range, the error will be increased rapidly, in this range, the BP network identification result is better. In this paper, we talk about the issue of handwritten numeral recognition, and proposes an identification method based on BP neural network. What we do is to change the location and size in the picture. We found that, they both directly affect picture recognition effect. This paper is firstly extracted the contour of the number, and then normalize them into the picture of. To do so, not only makes the image region the same size, but also in the image center. This makes the recognition more ideal, to achieve high identification purposes. In addition, we choose BP network with better tolerance, and200groups of handwritten digital image as the input vector, 110 groups of the other as recognition, the efficiency reached more than 90%. Also，we talk about another improvement about the handwriting recognition of BP. Network. With the development of computer network, more and more electronic prod