An Introduction to Deep Learning – A Empirical Study

Abstract

Deep learning (DL), a subset of machine learning (ML) and artificial intelligence (AI) it is considered as a core technology in today’s Industrial Revolution. Due to its learning capabilities from data, DL technology made from artificial neural network (ANN), it has become a one of the topics in the field of context of computing and is widely applied in various application areas like healthcare, visual recognition, text analytics, cybersecurity, and many more. In this pager we will be learning about the fundamental building blocks of deep learning which uses perceptron, stacking the perceptron together to solve more complex models by using mathematical optimize models using backpropagation and gradient descent. We will be learning practical challenges of training these models in the real life by applying best practices like adaptive learning, batching and regularization to struggle with overfitting.