Improvement of MNIST Image Recognition Based on CNN Article Swipe

View

Related Concepts

MNIST database Dropout (neural networks) Digit recognition Convolutional neural network Computer science Artificial intelligence Pattern recognition (psychology) Image (mathematics) Field (mathematics) Convergence (economics) Layer (electronics) Artificial neural network Deep learning Machine learning Mathematics Chemistry Economic growth Economics Pure mathematics Organic chemistry

Yifan Wang , Fenghou Li , Hai Sun , Wenbo Li , Cheng Zhong , Xuelian Wu , Hailei Wang , Ping Wang ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.1088/1755-1315/428/1/012097 · OA: W3000371668

At present, great progress has been made in the field of image recognition, especially in convolutional neural network. Lenet-5 convolutional neural network has been able to identify handwritten digit MNIST database with high precision. In this paper, experiments show that different activation functions, learning rates and the addition of the Dropout layer in front of the output layer will make the convergence speed different, weaken the influence of the initial parameters on the model, and improve the training accuracy. It is proved that the modified LeNet-5 model has a better improvement in handwritten digit recognition. This method is an efficient recognition method.