Read HandsOn Deep Learning Algorithms with Python Master Deep Learning algorithms with math by implementing them from scratch eBook Sudharsan Ravichandiran

Download As PDF : HandsOn Deep Learning Algorithms with Python Master Deep Learning algorithms with math by implementing them from scratch eBook Sudharsan Ravichandiran

Understand basic to advanced deep learning algorithms by implementing them from scratch, along with their practical applications

Key Features

Master the popular deep learning algorithms by implementing from scratch
Explains the underlying math behind the deep learning algorithms intuitively
Includes tips and best practices on choosing the right algorithm to solve a specific deep learning problem

Book Description

Deep learning is one of the prime and most talked-about domains in the AI space, allowing you to develop multi-layered models of varying complexities. The book helps you to master from the basic to the more advanced deep learning algorithms. Throughout the book, you will learn about an algorithm, the math behind it and how to implement it from scratch. Along with it, you will also learn how to use deep learning libraries such as TensorFlow and Keras for creating intelligent applications.

The book starts with explaining how to build your own neural network. Then you will understand gradient descent variants such as AdaDelta, Adam, Adamax and more. Later you will learn about the CNN architecture, and see how CNN is used in neural style transfer. Furthermore, you will understand how RNN and LSTM work, followed by learning about GANs and their types such as StackGAN, CycleGAN, and more. This book also covers the advanced deep learning algorithms such as Autoencoders, Hierarchical Attention Networks, and Restricted Boltzmann Machines, and the different real-world problems that can be solved using them.

By the end of this book, you will have all the knowledge and experience needed to implement deep learning in your projects, and you will be all set to conquer the world of deep learning.

What you will learn

Understand the fundamentals of Deep Learning
Learn Gradient Descent and its variants such as Adam, AMSGrad, and more
Implement various deep learning algorithms such as CNN, RNN, and LSTM from scratch
Understand GAN and different types of GANs such as DiscoGAN, StackGAN, and more
Master autoencoders, deep belief networks, and Restricted Boltzmann Machines
Perform document classification using Hierarchical Attention Networks

Who This Book Is For

This book is for machine learning engineers, data scientists, AI developers, and all those who want to focus on neural networks and deep learning. If you are completely new to deep learning but have some experience in machine learning and Python programming, this book will be a great resource to you as well.