Deep Learning Crash Course

by Giovanni Volpe, Benjamin Midtvedt, Jesús Pineda, Henrik Klein Moberg, Harshith Bachimanchi, Joana B. Pereira, Carlo Manzo
No Starch Press, San Francisco (CA), 2026
ISBN-13: 9781718503922
https://nostarch.com/deep-learning-crash-course

---

Deep Learning Crash Course is a comprehensive and up-to-date guide that takes you from simple neural networks all the way to cutting-edge deep learning architectures-no advanced math and programming required, just a basic knowledge of programming. From CNNs and GANs to Transformers and Diffusion Models, each chapter brings you hands-on, real-world projects so you can build and truly master the latest AI breakthroughs. Whether you’re an engineer, scientist, or just curious about AI, you’ll discover how to implement, optimize, and innovate with the full spectrum of modern deep learning techniques.

---

1. Building and Training Your First Neural Network
   Introduces single- and multi-layer perceptrons for classification tasks (e.g., MNIST digit recognition).

2. Capturing Trends and Recognizing Patterns with Dense Neural Networks
   Explores regression problems and digital twins, focusing on continuous-value prediction with multi-layer networks.

3. Processing Images with Convolutional Neural Networks
   Covers convolutional neural networks (CNNs) and their application to tasks such as image classification, localization, style transfer, and DeepDream.

4. Enhancing, Generating, and Analyzing Data with Autoencoders
   Focuses on autoencoders, variational autoencoders, Wasserstein autoencoders, and anomaly detection, enabling data compression and generation.

5. Segmenting and Analyzing Images with U-Nets
   Discusses U-Net architectures for image segmentation, cell counting, and various biomedical imaging applications.

6. Training Neural Networks with Self-Supervised Learning
   Explains how to use unlabeled data and the symmetries symmetries of a problem for improved model performance with an application in particle localization.

7. Processing Time Series and Language with Recurrent Neural Networks
   Uses recurrent neural networks (RNNs), GRUs, and LSTMs to forecast time-dependent data and build a simple text translator.

8. Processing Language and Classifying Images with Attention and Transformers
   Introduces attention mechanisms, transformer models, and vision transformers (ViT) for natural language processing (NLP) including improved text translation and sentiment analysis, and image classification.

9. Creating and Transforming Images with Generative Adversarial Networks
   Demonstrates generative adversarial networks (GAN) training for image generation, domain translation (CycleGAN), and virtual staining in microscopy.

10. Implementing Generative AI with Diffusion Models
    Presents denoising diffusion models for generating and enhancing images, including text-to-image synthesis and image super-resolution.

11. Modeling Molecules and Complex Systems with Graph Neural Networks
    Shows how graph neural networks (GNNs) can model graph-structured data (molecules, cell trajectories, physics simulations) using message passing and graph convolutions.

12. Continuously Improving Performance with Active Learning
    Describes techniques to iteratively select the most informative samples to label, improving model performance efficiently.

13. Mastering Decision-Making with Deep Reinforcement Learning
    Explains Q-learning and Deep Q-learning by teaching an agent to master games such as Tetris.

14. Predicting Chaos with Reservoir Computing
    Covers reservoir computing methods for forecasting chaotic systems such as the Lorenz attractor.

CC. Companion Examples
Provides additional examples complementing those in the book.

---