ADVANCEMENTS IN HANDWRITTEN TEXT RECOGNITION FOR UZBEK LANGUAGE

Abstract

The utilization of activation functions is a crucial aspect of neural
networks, including those involved in the recognition of handwritten text
images through convolutional neural networks. This article focuses on the
benefits and drawbacks of activation functions in this context and presents a
comparative analysis of various neural network models using different
activation functions. The results indicate that the organized convolutional neural
network achieved a recognition efficiency of 80 percent