[!IMPORTANT] This repository also hosts course materials, assessment resources, practice content, and complete session summaries for the Amazon ML Summer School 2025.
Students are encouraged to read, learn, revise, and practice using the provided material.
At the bottom of each module summary, you will find practice tasks and coding exercises to strengthen your understanding.
Apart from Amazon ML Summer School resources, this repository also contains an ocean of Machine Learning resources for deeper learning.
Explore the More ML Resources section for additional content, notes, roadmaps, and learning material.
Full curriculum and module-wise content are available below.

About the Program

The Amazon ML Summer School offers students a unique opportunity to learn Machine Learning from Amazon’s expert Scientists and industry leaders.
This comprehensive program covers essential ML concepts while providing insights into real-world applications used in modern AI systems.

Designed for students graduating in 2027 or 2028 from any recognized institute in India.

Key Highlights

• Learn core ML concepts from industry experts
• Explore domains such as Deep Learning, AI, NLP, Robotics, Computer Vision, Speech Recognition, Data Science, and Operations Research
• Interact directly with Amazon Scientists
• Internship opportunities with stipends up to ₹1.5 Lakh per month
• Pre-Placement Offers (PPOs) up to ₹51 LPA at Amazon and other top companies
• Build a strong foundation for ML interviews, research, and future careers in AI

Official Links

• Previous Year Program 2024: Amazon ML Summer School 2024
• Previous Year Program 2025: Amazon ML Summer School 2025
• Official Program Details: Amazon ML Summer School 2026
• Application Form: Apply Here

Selection Test Format

The selection test consists of two sections:

• Part A: 20 MCQs covering Machine Learning basics, Probability, Statistics, and Linear Algebra
• Part B: 2 Programming Questions

[!TIP] Both sections have separate cutoffs, so perform your best in each section.
Amazon strictly checks for plagiarism in coding submissions. Avoid sharing code or using unfair means during the assessment.

🕒 Total Duration: 60 Minutes

Contents of This Repository

• 📄 Programming Questions (2023): Coding questions asked during the 2023 selection assessment.
• 📄 Summer School 2023 MCQs: Multiple-choice questions asked in the 2023 selection test for revision.
• 📄 Summer School 2024 Questions: Complete question pool and exam layout from the 2024 cohort.
• 📃 Official Sample Test 2025: Official sample assessment shared by Scaler (Solved).
• 📘 Amazon ML Summer School Assessment 2025 (Set 1): Questions from the AMSS 2025 assessment held during the morning shift.
• 📘 Amazon ML Summer School Assessment 2025 (Set 2): Questions from the AMSS 2025 assessment held during the afternoon shift.
• 📂 AMSS 2025 Module Summaries: Core directory containing complete notes, curriculum overviews, and summaries for all 8 modules.
• 📚 More ML Resources: Additional Machine Learning roadmaps, conceptual notes, and deep-learning material.

[!NOTE] Having trouble opening a PDF?
If GitHub displays an error or fails to load a PDF link, it is due to a temporary GitHub rendering issue common on certain browsers. The PDF files themselves are completely functional.

• Fix: Simply click the "Download" button on the top-right corner of the file preview screen to save it and read it locally on your device.
• If the browser preview loads fine for you, feel free to study and practice directly on GitHub!

Curriculum – AMSS 2025

• Aug 9th 2025 – Module 1: Supervised Learning
• Aug 10th 2025 – Module 2: Deep Neural Networks
• Aug 16th 2025 – Module 3: Dimensionality Reduction
• Aug 17th 2025 – Module 4: Unsupervised Learning
• Aug 23rd 2025 – Module 5: Probabilistic Graphical Models
• Aug 24th 2025 – Module 6: Sequential Learning
• Aug 30th 2025 – Module 7: Causal Inference
• Aug 31st 2025 – Module 8: Reinforcement Learning

[!NOTE] Many online PDFs, notes, and PYQ collections available across different platforms are sourced from this repository, often without credit.
That is completely fine. The main goal is to help students prepare better, learn deeply, and succeed in the assessment and interviews.

[!IMPORTANT] ⭐ If you find this repository useful, consider giving it a star to support the project and help more students discover these resources.