Deep Learning Crash Course

A Hands-On, Project-Based Introduction to Artificial Intelligence

by Giovanni Volpe, Benjamin Midtvedt, Jesús Pineda, Henrik Klein Moberg, Harshith Bachimanchi, Joana B. Pereira, and Carlo Manzo

January 2026, 680 pp.

ISBN-13:

9781718503922

Download Chapter 3: Processing Images with Convolutional Neural Networks

Deep Learning Crash Course is a fast-paced, thorough introduction that will have you building today’s most powerful AI models from scratch. No experience with deep learning required!

Designed for programmers who may be new to deep learning, this book offers practical, hands-on experience, not just an abstract understanding of theory.

You’ll start from the basics, and using PyTorch with real datasets, you’ll quickly progress from your first neural network to advanced architectures like convolutional neural networks (CNNs), transformers, diffusion models, and graph neural networks (GNNs). Each project can be run on your own hardware or in the cloud, with annotated code available on GitHub.

You’ll build and train models to:

Classify and analyze images, sequences, and time series
Generate and transform data with autoencoders, GANs (generative adversarial networks), and diffusion models
Process natural language with recurrent neural networks and transformers
Model molecules and physical systems with graph neural networks
Improve continuously through reinforcement and active learning
Predict chaotic systems with reservoir computing

Whether you’re an engineer, scientist, or professional developer, you’ll gain fluency in deep learning and the confidence to apply it to ambitious, real-world problems. With Deep Learning Crash Course, you’ll move from using AI tools to creating them.

Author Bio

Giovanni Volpe, head of the Soft Matter Lab at the University of Gothenburg and recipient of the Göran Gustafsson Prize in Physics, has published extensively on deep learning and physics and developed key software packages including DeepTrack, Deeplay, and BRAPH. Benjamin Midtvedt and Jesús Pineda are core developers of DeepTrack and Deeplay. Henrik Klein Moberg and Harshith Bachimanchi apply AI to nanoscience and holographic microscopy. Joana B. Pereira, head of the Brain Connectomics Lab at the Karolinska Institute, organizes the annual conference Emerging Topics in Artificial Intelligence. Carlo Manzo, head of the Quantitative Bioimaging Lab at the University of Vic, is the founder of the Anomalous Diffusion Challenge.

Table of contents

Introduction

Chapter 1: Building and Training Your First Neural Network
Chapter 2: Capturing Trends and Recognizing Patterns with Dense Neural Networks
Chapter 3: Processing Images with Convolutional Neural Networks
Chapter 4: Enhancing, Generating, and Analyzing Data with Autoencoders
Chapter 5: Segmenting and Analyzing Images with U-Nets
Chapter 6: Training Neural Networks with Self-Supervised Learning
Chapter 7: Processing Time Series and Language with Recurrent Neural Networks
Chapter 8: Processing Language and Classifying Images with Attention and Transformers
Chapter 9: Creating and Transforming Images with Generative Adversarial Networks
Chapter 10: Implementing Generative AI with Diffusion Models
Chapter 11: Modeling Molecules and Complex Systems with Graph Neural Networks
Chapter 12: Continuously Improving Performance with Active Learning
Chapter 13: Mastering Decision-Making with Deep Reinforcement Learning
Chapter 14: Predicting Chaos with Reservoir Computing

Conclusion
Index

View the detailed Table of Contents
View the Index

Reviews

"This is a book that rewards effort. It respects the reader’s intelligence without assuming expertise, and it delivers one of the most practical learning experiences I have encountered in AI education. For anyone serious about moving from AI observer to AI builder, this book is a strong recommendation."
—Antoine Tardif, Founder & CEO, Unite.AI

Extra Stuff

Additional resources and code examples for this title can be found at the book's GitHub page.