Source
Telegram: book_cube
Detailed review with chapter-by-chapter notes and practical commentary.
Глубокое обучение и анализ данных. Практическое руководство
Authors: Дмитрий Малов
Publisher: БХВ-Петербург, 2023
Length: 270 pages
A concise intro to deep learning and data science: fundamentals, classical ML algorithms, hands-on tasks, and practical walkthroughs with TensorFlow, Keras, and PyTorch.
What this book covers
This is a compact intro to deep learning and data science: fundamentals first, then practical tasks, and finally implementation patterns in three mainstream frameworks.
It is most useful as a fast orientation map before starting your own experiments.
Structure: 8 chapters
Machine learning foundations
Linear algebra, probability basics, and core ML task framing: classification, regression, anomaly detection, translation, synthesis. Includes a brief Python/OOP and development-process overview.
Core machine learning algorithms
Data preprocessing, dimensionality reduction, linear/logistic regression, decision trees, SVM, naive Bayes, k-means, kNN, random forest, and gradient boosting.
Deep learning foundations
Backpropagation, perceptron, Markov chains, Boltzmann machine, Hopfield network, CNN, RNN, transformers, autoencoders, and GANs.
Data science foundations
CRISP-DM methodology, key ML team roles (analyst, data engineer, data scientist), trends like deepfakes/AutoML/MLOps, and a TensorFlow/PyTorch/Keras overview.
Deep learning tasks
Hands-on examples: data augmentation, computer vision with OpenCV, symbol recognition, NLP, audio processing, and video processing.
TensorFlow
Applying chapter 5 tasks using TensorFlow.
Keras
Rebuilding practical tasks through the higher-level Keras API.
PyTorch
Implementing the same class of tasks in the PyTorch ecosystem.
What is most useful
- A compact and readable intro that quickly maps the space from math basics to applied tasks.
- The companion repository is useful as a starting point for hands-on experimentation.
- Works well as a bridge between introductory theory and first practical deep learning projects.
What to keep in mind
- Coverage is broad, so many topics are high-level rather than deep.
- Chapter 2 is dense and can be hard to follow for complete beginners.
- To build strong practical confidence, you will likely need extra sources on math and ML.
Practice
GitHub repository
Code and charts from the book for replaying and adapting examples.
How to get maximum value from it
Use chapters 1-4 to align vocabulary and fundamentals.
Run and modify repository code while going through chapters 5-8.
After finishing, move to production-focused AI and modern LLM system resources.
Related chapters
- Why engineers should know ML and AI - Provides the AI/ML section map and shows where this book fits in the broader learning path.
- Precision and Recall Basics - Reinforces core classification-quality metrics needed for practical tasks from the book.
- AI Engineering (short summary) - Extends the path from foundational ML practice to production approaches for AI and LLM systems.
- Hands-On Large Language Models (short summary) - Bridges from classical deep learning to modern LLMs, embeddings, and RAG patterns.
- Prompt Engineering for LLMs (short summary) - Expands the applied track with prompt and context engineering practices for LLM applications.