Kitoblar

Must-read (asosiy)

Klassik ML

• "Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow" — Aurélien Géron (3-nashr, 2022)

• Eng tavsiya etiladigan kitob. Boshidan oxirigacha o'qing.

• Topish: kitob do'konlari, O'Reilly Online Learning, Z-Library

• "Python for Data Analysis" — Wes McKinney (3-nashr, 2022, bepul online)

• Pandas yaratuvchisidan

• Bepul: wesmckinney.com/book

MLOps

• "Designing Machine Learning Systems" — Chip Huyen (2022) — MLOps bibliya

• Production ML uchun eng zo'r kitob

• Har kompaniyada o'qiladi

• "Machine Learning Engineering" — Andriy Burkov (2020)

• Practical, qisqa va aniq

• Bepul read online (1 hafta): leanpub.com

Deep Learning

• "Deep Learning with PyTorch" — Eli Stevens, Luca Antiga, Thomas Viehmann

• PyTorch official kitobi

• Bepul PDF: pytorch.org/deep-learning-with-pytorch

• "Dive into Deep Learning (D2L)" — Aston Zhang et al. (bepul online)

• Interactive — har kontseptsiyaga to'liq kod

• d2l.ai

Strong recommendation

Matematika

• "Mathematics for Machine Learning" — Deisenroth, Faisal, Ong (bepul PDF)

• ML uchun zarur matematika

• mml-book.com

• "Why Machines Learn" — Anil Ananthaswamy (2024)

• Math intuition (less formula)

LLM / Modern AI

• "Hands-On Large Language Models" — Jay Alammar, Maarten Grootendorst (O'Reilly, 2024)

• Eng yangi va eng yaxshi LLM kitobi

• Visual va praktik

• "Build a Large Language Model (From Scratch)" — Sebastian Raschka (2024)

• GPT-style LLM'ni noldan qurish

Statistics / Data Science

• "An Introduction to Statistical Learning (ISLR)" — James, Witten, Hastie, Tibshirani (bepul)

• Statistik o'rganishning klassik kitobi

• statlearning.com (Python versiyasi ham bor)

• "Practical Statistics for Data Scientists" — Bruce, Bruce, Gedeck

• DS uchun zarur statistika

Computer Vision

• "Deep Learning for Computer Vision" — Adrian Rosebrock (PyImageSearch)
• Praktik, ko'p loyiha bilan

NLP

• "Natural Language Processing with Transformers" — Lewis Tunstall (HuggingFace) (2022)

• HuggingFace ekosistemasi uchun bibliya

• "Speech and Language Processing" — Jurafsky & Martin (bepul, 3-nashr draft)

• Klassik NLP referensi

• web.stanford.edu/~jurafsky/slp3

Nice to read

Production / SWE

• "Effective Python" — Brett Slatkin (2-nashr)
• "Architecture Patterns with Python" — Percival, Gregory
• "Designing Data-Intensive Applications" — Martin Kleppmann
• "Site Reliability Engineering" — Google (bepul: sre.google/books)

MLOps deeper

• "Building Machine Learning Pipelines" — Hannes Hapke & Catherine Nelson
• "Reliable Machine Learning" — Cathy Chen, Niall Murphy
• "Practical MLOps" — Noah Gift

Specialized

• "Recommender Systems Handbook" — Ricci, Rokach, Shapira
• "Reinforcement Learning: An Introduction" — Sutton & Barto (bepul PDF)
• "Generative Deep Learning" — David Foster (GANs, VAEs)

Career

• "AI Superpowers" — Kai-Fu Lee — industry overview
• "Machine Learning Yearning" — Andrew Ng (bepul) — practical tips
• "The Hundred-Page Machine Learning Book" — Andriy Burkov — qisqa overview

Reference books

• "Pattern Recognition and Machine Learning" — Bishop (advanced)
• "The Elements of Statistical Learning" — Hastie, Tibshirani, Friedman (advanced)
• "Deep Learning" — Goodfellow, Bengio, Courville (advanced theory)

Qanday o'qish?

O'qish strategiyasi

1. Bittada bitta kitob — bir nechta o'qish - nimani ham aniqlamasdir
2. Project-driven — kitobni 100% emas, kerakli bo'limni o'qing
3. Notebook bilan — har kontseptsiyani o'zingiz kodda sinab ko'ring
4. Tezda eshitilishi — ba'zi kitoblar Audible'da bor

Tartib (yangi boshlovchilar uchun)

1. Géron — Hands-On ML(Oy 1-3 davomida)
2. McKinney — Python for Data Analysis(Oy 1)
3. Huyen — Designing ML Systems(Oy 4-6)
4. Alammar — LLMs(Oy 5)

Bepul kitoblar to'plami

Onlayn kurslar ga o'tish.