ARCHIVES

Abstract: The stochastic gradient descent optimization approach is used to train deep learning neural networks in this paper. Artificial neural networks are a subfield of deep learning that uses algorithms inspired by the structure and function of the brain. Deep learning systems are designed to learn feature hierarchies based on the composition of lower level characteristics at the top of the hierarchy. The various sorts of learning models are also discussed. We build a train and dataset with different samples (500, 2000, and 4000) and change the Epochs value in this research (100, 300 and 400).We also create learning curves for different momentums. In This paper we create learning curves for different momentums.