No abstract

No abstract

Since Geoffrey Hinton first proposed the concept of deep learning in 2006, which in Reducing the dimensionality of data with neural networks, deep learning has been the continuous concern of the researchers. Deep learning uses a multilayer neural network to simulate the multi-layer abstract learning process of the human brain. The network structure design and feature extraction are the key problems in the application of data mining and pattern recognition. The accuracy of deep learning for handwritten digital recognition has always been an important criterion for measuring a deep learning algorithm or network structure. In this paper, a handwritten character recognition algorithm based on convolution neural network is studied and compared with other recognition algorithms, and the error rate in their recognition is compared.

No abstract