by Benjamin Midtvedt, Jesús Pineda, Henrik Klein Moberg, Harshith Bachimanchi, Joana B. Pereira, Carlo Manzo, Giovanni Volpe
No Starch Press, San Francisco (CA), 2025
ISBN-13: 9781718503922
https://nostarch.com/deep-learning-crash-course

1. Dense Neural Networks for Classification
   Introduces single- and multi-layer perceptrons for classification tasks (e.g., MNIST digit recognition).

• Code 1-1: Classifying 1D Data with a Single Neuron
  Implements a single artificial neuron to classify 1D data into binary classes using a step function. The example walks through loading the dataset, visualizing the results, and training the neuron to improve its predictions using a gradient descent method.

• Code 1-2: Classifying 2D Data with a Single Neuron
  Extends the single-neuron concept to classify 2D data. The code introduces weight updates for multidimensional input, visualization of classification boundaries, and evaluation on clean and noisy datasets.

• Code 1-3: Training a Dense Neural Network with Error Backpropagation
  Demonstrates training a two-layer dense neural network using the backpropagation algorithm. This code calculates gradients and updates weights iteratively to minimize the classification error on 2D data.

• Code 1-A: Classifying the MNIST Digits with a Dense Neural Network
  Implements a fully connected neural network with two hidden layers to classify handwritten digits from the MNIST dataset. The example includes data loading, training, evaluation using confusion matrices, and failure analysis to identify misclassified samples.

2. Dense Neural Networks for Regression

3. Convolutional Neural Networks for Image Analysis

4. Encoders–Decoders for Latent Space Manipulation

5. U-Nets for Image Transformation

6. Self-Supervised Learning to Exploit Symmetries

7. Recurrent Neural Networks for Timeseries Analysis

8. Attention and Transformers for Sequence Processing

9. Generative Adversarial Networks for Image Synthesis

10. Diffusion Models for Data Representation and Exploration

11. Graph Neural Networks for Relational Data Analysis

12. Active Learning for Continuous Learning

13. Reinforcement Learning for Strategy Optimization

14. Reservoir Computing for Predicting Chaos