<Hands-On Machine Learning with Scikit-Learn, PyTorch> Complete Reading Challenge

Challenge Schedule

• Registration period: 10/8 (Thu) ~ 11/1 (Sun)

• Challenge schedule: 2026/11/2 (Mon)–2027/3/14 (Sun) (19 weeks)

• Weekly reading: Complete one chapter per week, from Chapter 1 through Chapter 19

  
  

• A certificate of completion will be issued if you complete the missions and reach a 100% attendance rate during the challenge period. If you fail to complete the missions, we will not be able to issue a certificate.

• The challenge mission includes proof of book purchase. You can verify both paper books and e-books!

• When signing up for the challenge, please be sure to enter your name, phone number, and email in the survey. This information will be needed later when Hanbit+ (https://www.hanbit.co.kr/) mileage is provided.

  
  

Challenge Benefits

• Benefits of joining the challenge (issued on November 2)

  • You can take the <Hands-On Machine Learning with Scikit-Learn and PyTorch> online course (to be produced) at your own pace.

  • <Hands-On Machine Learning with Scikit-Learn and PyTorch Code Explained> Inflearn paid course (to be produced) with a free coupon (worth 150,000 won)

    
    

  • <Learn LLMs by Building Them from Scratch> Inflearn paid course (https://inf.run/yaC3L) 50% discount coupon available (worth 45,000 won)

  • <Machine Learning, Quickly Learn the Essentials!> Inflearn paid course (https://inf.run/1cv1q) 50% discount coupon provided (worth 20,000 won)

  • <Large Language Models, the Essentials—Fast!> Inflearn paid course (https://inf.run/njgW2) 50% off coupon provided (worth 20,000 won)

• Additional benefits upon completing the challenge

  • Upon completing week 10 of the challenge: Earn 10,000 mileage points that can be used like cash on the Hanbit+ website (https://www.hanbit.co.kr/)awarded after week 10 ends)

  • Upon completing the entire challenge: Receive an additional 10,000 points in mileage that can be used like cash on the Hanbit+ website (https://www.hanbit.co.kr/)paid after the end of Week 19)

  • Among those who sign up during the early bird period (10/8–10/21), 10 people will be randomly selected to receive a coffee coupon (worth 5,000 won).

  • For this event, the information of those who complete the challenge will be provided to Hanbit Media, which will then provide guidance on the point distribution.

    
    

• The benefits for signing up for the challenge are provided as an Inflearn coupon. Please be sure to check the important notes below.

<Important Notes> Must Read!!!

• For those who joined the challenge on November 2, the free coupon issuance link for the “Hands-On Machine Learning with Scikit-Learn, PyTorch Code Explanations” course and the 50% discount coupon issuance link for the “Learn LLMs by Building from Scratch,” “Machine Learning, Fast-Track the Essentials!,” and “Large Language Models, Fast-Track the Essentials!” courses will be sent to the email address registered with Inflearn.

• Please check in advance whether you can receive emails from Inflearn. If the email is treated as spam, we will not be able to reissue it later. If you have any problems receiving emails from Inflearn, please contact the Inflearn Help Desk.

• This link is valid for 3 days. You must use the link to claim the free and discount coupons within 3 days. Once 3 days have passed, the link will become invalid and you will not be able to claim the coupons!

• You must use the issued coupons within 1 day!

Book Introduction

Don’t stop at using AI—understand how AI is made

Now that generative AI and LLMs have become part of everyday life, simply learning new tools is not enough to truly understand AI. Underneath it all, the fundamental principles of machine learning—preparing data, selecting models, training, and evaluating—remain firmly in place. With this book, learn the fundamental concepts of machine learning and end-to-end projects with scikit-learn, then implement neural networks yourself with PyTorch and gradually expand your understanding of the principles of deep learning.
If you have read *Hands-On Machine Learning (3rd Edition)*, the familiar fundamentals remain largely the same, but the content after deep learning has changed considerably. You will relearn neural networks with a focus on PyTorch, expanding your scope from transformers for natural language processing and chatbots to vision, multimodal systems, and model acceleration. You will work directly with and fine-tune Hugging Face’s pretrained models and LLMs, then apply what you learn to autoencoders, GANs, diffusion models, and reinforcement learning through practical code and examples. In fact, this edition has been completely reorganized around PyTorch in its entirety Part II and adds three new chapters on transformers.
Rather than chasing individual cutting-edge technologies one by one, if you want to start with the fundamentals of machine learning and understand how today’s AI technologies have evolved, this book will serve as a reliable guide. For readers just starting out, it provides a solid foundation; for readers who have already read the third edition, it offers a natural path to the next level with PyTorch and the latest AI technologies, building on the fundamentals they have already learned.

Testimonials

Experts who read it first recommend this book

• "This book is the ultimate map for exploring the unknown world of machine learning. Always keep it within reach."

  — Haeseon Park, Google AI/Cloud GDE

• "This is the book that has trained a generation of machine learning engineers. This time, covering PyTorch, it will once again be the ultimate hands-on guide."

  — Tarun Narayanan, Amazon AGI Machine Learning Engineer

• "It's an excellent introduction for those who feel overwhelmed by how AI is created and ultimately reaches our hands. It will be a great guide, building steadily from the basics to the depths."

  — Shin Jeong-gyu, CEO of Lablup · Google Developer Expert (AI·Cloud)

• "It guides you step by step from the basic concepts to the latest techniques with well-structured code and practical examples. You can learn by implementing them yourself with scikit-learn and PyTorch."

  — Louis-François Bouchard, Co-founder and CTO of Towards AI

• [Kyobo Book Centre] [Yes24] [Aladin] [Hanbit Media]

• 1,1112 pages, paperback: 66,000 won –> 59,400 won, e-book: 52,800 won –> 47,520 won