What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Key benefits

Understand the theory, mathematical foundations and structure of deep neural networks

Become familiar with transformers, large language models, and convolutional networks

Learn how to apply them to various computer vision and natural language processing problems

Purchase of the print or Kindle book includes a free PDF eBook

Description

The field of deep learning has developed rapidly recently and today covers a broad range of applications. This makes it challenging to navigate and hard to understand without solid foundations. This book will guide you from the basics of neural networks to the state-of-the-art large language models in use today. The first part of the book introduces the main machine learning concepts and paradigms. It covers the mathematical foundations, the structure, and the training algorithms of neural networks and dives into the essence of deep learning. The second part of the book introduces convolutional networks for computer vision. We’ll learn how to solve image classification, object detection, instance segmentation, and image generation tasks. The third part focuses on the attention mechanism and transformers – the core network architecture of large language models. We’ll discuss new types of advanced tasks they can solve, such as chatbots and text-to-image generation. By the end of this book, you’ll have a thorough understanding of the inner workings of deep neural networks. You'll have the ability to develop new models and adapt existing ones to solve your tasks. You’ll also have sufficient understanding to continue your research and stay up to date with the latest advancements in the field.

What you will learn

Establish theoretical foundations of deep neural networks

Understand convolutional networks and apply them in computer vision applications

Become well versed with natural language processing and recurrent networks

Explore the attention mechanism and transformers

Apply transformers and large language models for natural language and computer vision

Implement coding examples with PyTorch, Keras, and Hugging Face Transformers

Use MLOps to develop and deploy neural network models

What do you get with eBook?

Instant access to your Digital eBook purchase

Download this book in EPUB and PDF formats

Access this title in our online reader with advanced features

DRM FREE - Read whenever, wherever and however you want

AI Assistant (beta) to help accelerate your learning

Frequently bought together

50 Algorithms Every Programmer Should Know

$49.99

$49.99

Machine Learning Engineering with Python

$49.99

Total $ 149.97

Didi Jan 15, 2024

Deep learning (DL) has taken the world by storm, revolutionizing entire fields such as computer vision and natural language processing. This comprehensive book is a wonderful and practical resource for understanding DL from the ground up, and covers the most important areas of DL applications, including computer vision, natural language processing (NLP), and large language models (LLMs).The book begins with a clear and detailed overview of machine learning, neural networks, and the fundamentals of deep learning. It proceeds with detailed examples of useful computer vision models and applications, such as object detection, image segmentation, and image generation using diffusion models. A significant part of the book is dedicated to models for natural language processing and LLMs, including an in-depth description of the transformer architecture, which is at the heart of such models these days. The last part of the book is focused on developing and deploying DL models in practice (aka MLOps).I especially liked the practical, hands-on approach taken by the author, where helpful code examples accompany the textual descriptions, and greatly assist in reinforcing the materials and concepts presented in the book. The accompanying GitHub repository includes all code examples, and is very useful as well.This practical guide will benefit any software engineer, researcher, data scientist or machine learning practitioner who wants to better understand how to build real-world DL models for computer vision and natural language processing. Prior familiarity with the Python programming language will be very helpful to fully benefit from this book.Highly recommended!

Amazon Verified review

Patrick Nicolas Sep 26, 2024

I liked:This book offers a thorough introduction that gradually increases in complexity, making it ideal for novice data scientists, while experienced machine learning professionals will find numerous practical insights to help avoid common pitfalls in model development.Each chapter is accompanied by relevant Python code, allowing readers to explore the implementations on the go via a tablet or smartphone, without needing to access GitHub or an editor. Chapters are well-structured, including valuable highlights and concluding with helpful takeaways.The author incorporates familiar diagrams and illustrations from well-established and foundational papers, creating a sense of continuity for readers familiar with the field.I personally appreciated the in-depth focus on often underrepresented topics, such as activation functions, mixed-precision training, various word embeddings, and conditioning transformers, among others. There's also a well-rounded section on MLOps, which includes tools like ONNX operators, TensorBoard, and Flask for deployment (although it would have been nice to see FastAPI as an alternative).Suggestions:The book would benefit from a clear statement of the Python and NumPy versions used, although I encountered only a minor issue when running the sample code with Python 3.12 and NumPy 2.1.1.While the discussions of older deep learning models, such as Inception networks or YOLO, provide valuable historical context, these sections may not appeal to all readers.One last note:This edition replaces the previous chapters on reinforcement learning with a more detailed introduction to transformers and their implementation.Conclusion:Overall, this is a well-crafted and informative deep learning book, enriched with well-documented Python code. It will appeal to both beginner and veteran data scientists, as well as software engineers.

Amazon Verified review

Ryan Kreisel Dec 06, 2023

The book's structure is thoughtfully crafted, starting with foundational concepts and gradually progressing to advanced topics, ensuring a smooth learning curve for readers of all levels. Moreover, Ivan Vasilev writing style is engaging and clear, making even the most intricate concepts digestible. But what truly sets "Python Deep Learning" apart is its relevance in the rapidly evolving landscape of artificial intelligence. And if you can't decide on Kindle or Paperback, the cover is pretty stylish and sits great on the bookshelf once you have read it.

Amazon Verified review

H2N Dec 14, 2023

This book, Python Deep Learning, introduces different key architectures such as transformers, LLMs and convolutional networks. It is helpful for someone who wants to start to explore deep learning approach and also good for experts such as programmer, developers, data scientists. The book covers from theoretical concepts to practical coding in PyTorch, Keras and Hugging Face Transformers, making advanced topics approachable through a combination of theory and real world application.

Amazon Verified review

KP Dec 19, 2023

Python Deep Learning is an exceptional resource that takes readers on an enlightening journey through the intricacies of neural networks, providing a comprehensive guide for both beginners and seasoned practitioners. The book combines clear explanations, practical examples (including code), and hands-on exercises to make the complex world of deep learning accessible to all. The writing is clear, concise, and avoids unnecessary jargon, making it an ideal companion for readers with varying levels of expertise.The practical examples and code snippets are thoughtfully crafted, enabling readers to experiment with the concepts introduced in each chapter. Additionally, the book includes numerous real-world case studies and applications, ranging from image recognition and natural language processing to reinforcement learning. This diversity allows readers to appreciate the versatility of deep learning across various domains.This book is a gem for anyone looking to master neural networks using Python. Highly recommended.

Amazon Verified review

Python Deep Learning: Understand how deep neural networks work and apply them to real-world tasks , Third Edition

What do you get with eBook?