Key features
This book, "Deep Learning: Principles and Implementations", is intended as a text for core courses in machine learning taught to majors in engineering or computer science. It should also prove useful to engineers and researchers who wish to apply deep learning approaches to their projects.
It provides a comprehensive coverage of deep learning, ranging from linear regression and neural networks to advanced topics such as diffusion models and reinforcement learning.
It presents a step-by-step development of models from concepts and mathematical foundations to algorithms and implementations.
Each chapter includes complete Python code and dedicated exercises to support both practical learning and conceptual understanding.
Resources
Chapter Materials (under construction)
Ch. 1 — Introduction to Deep Learning
Slides
Solutions
Ch. 2 — Linear Regression
Slides
Solutions
Ch. 3 — Classification & Logistic Regression
Slides
Solutions
Ch. 4 — Basics of Neural Networks
Slides
Solutions
Ch. 5 — Practical Considerations in Neural Networks
Slides
Solutions
Ch. 6 — Introduction to PyTorch
Slides
Solutions
Ch. 7 — Convolutional Neural Networks
Slides
Solutions
Ch. 8 — Classic CNN Architectures
Slides
Solutions
Ch. 9 — Object Detection (YOLO)
Slides
Solutions
Ch. 10 — Probabilistic Generative Models
Slides
Solutions
Ch. 11 — Generative Adversarial Networks
Slides
Solutions
Ch. 12 — Diffusion Models
Slides
Solutions
Ch. 13 — Word Embedding
Slides
Solutions
Ch. 14 — Recurrent Neural Networks
Slides
Solutions
Ch. 15 — Transformer
Slides
Solutions
Ch. 16 — Introduction to Reinforcement Learning
Slides
Solutions
Ch. 17 — Deep Q-Learning
Slides
Solutions
Ch. 18 — Policy Gradient Methods
Slides
Solutions
Python Code Repository (under construction)
Full implementation code for all chaptersJupyter notebooks, datasets, and training scripts
GitHub Repository →Errata (under construction)
Page 45 — Equation corrected in Section 3.2
Download Full Errata