PyTorch Programming Playbook For Beginners: A Practical Guide to Tensors, Neural Networks, Model Training, and AI Development (PyTorch Programming Series) - Softcover

Book 1 of 3: PyTorch Programming Series

Marsh, Alvin

9798171172947: PyTorch Programming Playbook For Beginners: A Practical Guide to Tensors, Neural Networks, Model Training, and AI Development (PyTorch Programming Series)

Softcover

ISBN 13: 9798171172947

Publisher: Independently published, 2026

View all copies of this ISBN edition

0 Used

3 New

From US$ 25.00

PyTorch Programming Playbook For Beginners provides a practical introduction to PyTorch for readers who want to move beyond machine learning theory and start building real models with code.
The book begins with the foundations of PyTorch, explaining tensors, tensor operations, computational graphs, automatic differentiation, and the core concepts needed to understand how PyTorch works. It then progresses into neural networks, datasets, data loaders, loss functions, optimizers, training loops, validation, and model evaluation.
Rather than treating PyTorch as a collection of disconnected APIs, the book develops an understanding of how the major components work together in a complete machine learning workflow. Readers learn how to prepare data, construct neural network architectures, train models, diagnose problems, improve performance, and organize PyTorch projects effectively.
What You Will Learn

Understand PyTorch tensors and tensor operations
Work with CPU and GPU computation
Use automatic differentiation and autograd
Build neural networks with torch.nn
Prepare datasets and create data pipelines
Implement training and validation loops
Work with loss functions and optimizers
Monitor and evaluate model performance
Save and load trained models
Identify and troubleshoot common training problems
Build practical neural network projects
Develop a foundation for more advanced deep learning with PyTorch

Written for beginners while maintaining practical depth, this book provides the foundation needed to confidently move into more advanced deep learning techniques and real-world PyTorch development.

"synopsis" may belong to another edition of this title.