Use PyTorch to build end-to-end artificial intelligence systems using Python
- Build smart AI systems to handle real-world problems using PyTorch 1.x
- Become well-versed with concepts such as deep reinforcement learning (DRL) and genetic programming
- Cover PyTorch functionalities from tensor manipulation through to deploying in production
Artificial Intelligence (AI) continues to grow in popularity and disrupt a wide range of domains, but it is a complex and daunting topic. In this book, you’ll get to grips with building deep learning apps, and how you can use PyTorch for research and solving real-world problems.
This book uses a recipe-based approach, starting with the basics of tensor manipulation, before covering Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) in PyTorch. Once you are well-versed with these basic networks, you’ll build a medical image classifier using deep learning. Next, you’ll use TensorBoard for visualizations. You’ll also delve into Generative Adversarial Networks (GANs) and Deep Reinforcement Learning (DRL) before finally deploying your models to production at scale. You’ll discover solutions to common problems faced in machine learning, deep learning, and reinforcement learning. You’ll learn to implement AI tasks and tackle real-world problems in computer vision, natural language processing (NLP), and other real-world domains.
By the end of this book, you’ll have the foundations of the most important and widely used techniques in AI using the PyTorch framework.
What you will learn
- Perform tensor manipulation using PyTorch
- Train a fully connected neural network
- Advance from simple neural networks to convolutional neural networks (CNNs) and recurrent neural networks (RNNs)
- Implement transfer learning techniques to classify medical images
- Get to grips with generative adversarial networks (GANs), along with their implementation
- Build deep reinforcement learning applications and learn how agents interact in the real environment
- Scale models to production using ONNX Runtime
- Deploy AI models and perform distributed training on large datasets
Who this book is for
This PyTorch book is for AI engineers who are just getting started, machine learning engineers, data scientists and deep learning enthusiasts who are looking for a guide to help them solve AI problems effectively. Working knowledge of the Python programming language and a basic understanding of machine learning are expected.
Table of Contents
- Working with Tensors Using PyTorch
- Dealing with Neural Networks
- Convolutional Neural Networks for Computer Vision
- Recurrent neural networks for NLP
- Transfer Learning and TensorBoard
- Exploring Generative Adversarial Networks
- Deep Reinforcement Learning
- Productionizing AI models in PyTorch