Grokking Machine Learning, Second Edition, Version 3, MEAP, Serrano L.G., 2026

Grokking Machine Learning, Second Edition, Version 3, MEAP, Serrano L.G., 2026.

   This book is for anyone who wants to really understand machine learning (ML), not just treat it as a black box or reproduce examples blindly. If you have been curious about ML but felt that the math looked intimidating or the explanations too abstract, you are in the right place. We will use some math, but not heavy formality. The core ideas are explained with intuition, pictures, and stories, while the more formal details live in appendices you can visit when and if you want to.




Going from understanding to creating: Generative machine learning!
As you've learned so far, machine learning is very useful for answering questions like "is this email spam?", "does this image contain a cat?", or "how much would this house cost?" In fact, predictive machine learning is all about answering multiple choice questions (classification) or numerical questions (regression). In recent years we've seen many advances in another field called generative machine learning. In short, if predictive machine learning is like answering multiple choice questions, generative machine learning is like answering essay type questions. Generative machine learning models like transformers will be able to write text with great eloquence, and diffusion models will be able to draw very realistic pictures. As you can imagine, generative machine learning is much harder than predictive machine learning (in the same way that for a human, writing an essay or drawing a picture is harder than answering multiple choice questions).

The big jump between predictive and generative machine learning is similar to the jump between understanding a topic, and being able to create new material in that topic. This happens a lot in real life; for example, when you learn a new language, there is a period where you understand it and even be able to answer simple questions in the language. However, it takes more time and effort to be able to speak the language eloquently. ML models have two aspects, the understanding and the creating, and as you may imagine, the creating part is much harder than the understanding part.

Contents.
1 What is machine learning? It is common sense, except done by a computer.
2 Types of machine learning.
3 Drawing a line close to our points: Linear regression.
4 Optimizing the training process: Underfitting, overfitting, testing, and regularization.
5 Using lines to split our points: The perceptron algorithm.
6 A continuous approach to splitting points: Logistic classifiers.
7 How do you measure classification models? Accuracy and its friends.
8 Using probability to its maximum: The naive Bayes model.
9 Splitting data by asking questions: Decision trees.
10 Combining building blocks to gain more power: Neural networks.
11 Finding boundaries with style: Support vector machines and the kernel method.
12 Combining models to maximize results: Ensemble learning.
13 Putting it all in practice: A real-life example of data engineering and machine learning.
14 AI for language and image generation.
Appendix A. Solutions to the exercises.
Appendix B. The math behind gradient descent.
Appendix C. References.



Бесплатно скачать электронную книгу в удобном формате, смотреть и читать:
Скачать книгу Grokking Machine Learning, Second Edition, Version 3, MEAP, Serrano L.G., 2026 - fileskachat.com, быстрое и бесплатное скачивание.

Скачать файл № 1 - pdf
Скачать файл № 2 - epub
Ниже можно купить эту книгу, если она есть в продаже, и похожие книги по лучшей цене со скидкой с доставкой по всей России.Купить книги


Скачать - epub - Яндекс.Диск.

Скачать - pdf - Яндекс.Диск.




Теги: учебник по информатике :: информатика :: компьютеры :: Serrano