A Study on Dropout Techniques to Reduce Overfitting in Deep Neural Networks

Recently, neural networks are used in various applications to solve complex problems. The neural network creates models that can solve problems through training from data. However, overfitting problems in training models have a significant impact on the performance of a neural network. In this paper, the effect of dropout to reduce overfitting in neural networks is analyzed through experiments. It also analyzes the effect on the performance of neural networks according to the number of nodes in layers that is an important factor in designing neural network models. The results of these experiments will help to design the dropout rates and the number of nodes in layers to apply neural networks in various applications.