This repository is a curated collection of AI and Machine Learning resources shared by the Manipal Open Source Society AI Chapter, maintained by Akhil Varanasi (Head of AI). It is designed to help juniors and community members deepen their AI knowledge and accelerate their projects.
- 📚 Tutorials & Guides
- 🧑💻 Coding Practice & Projects
- 📊 Research Papers & Articles
- 🛠️ Tools & Libraries
- 🎥 Video Lectures & Workshops
- 💡 AI Concepts & Notes
𝟭. 𝗣𝗿𝗼𝗴𝗿𝗮𝗺𝗺𝗶𝗻𝗴 𝗕𝗮𝘀𝗶𝗰𝘀 (𝟭-𝟮 𝗪𝗲𝗲𝗸𝘀) → Pick Python (you’ll use it for everything). → Focus on: Loops, functions, object-oriented programming. → Tools: Jupyter Notebook, VS Code. Resource: Google’s Python Class → https://lnkd.in/d9yFJYXP
𝟮. 𝗠𝗮𝘁𝗵𝗲𝗺𝗮𝘁𝗶𝗰𝘀 𝗙𝗼𝘂𝗻𝗱𝗮𝘁𝗶𝗼𝗻𝘀 (𝟮-𝟯 𝗪𝗲𝗲𝗸𝘀) → Topics: Linear Algebra (vectors, matrices), Calculus (derivatives), Probability. → Tools: NumPy for practice. Resource: Mathematics for Machine Learning → mml-book.github.io
𝟯. 𝗦𝘁𝗮𝘁𝗶𝘀𝘁𝗶𝗰𝘀 & 𝗗𝗮𝘁𝗮 𝗔𝗻𝗮𝗹𝘆𝘀𝗶𝘀 (𝟮-𝟯 𝗪𝗲𝗲𝗸𝘀) → Key Skills: Exploratory Data Analysis (EDA), hypothesis testing, correlation. → Tools: Pandas, Matplotlib, Seaborn. Resource: Kaggle’s Pandas Course → kaggle.com/learn/pandas
𝟰. 𝗗𝗮𝘁𝗮 𝗖𝗹𝗲𝗮𝗻𝗶𝗻𝗴 (𝟭-𝟮 𝗪𝗲𝗲𝗸𝘀) → Learn how to handle missing data, outliers, and feature scaling. → Tools: Pandas, Scikit-learn. Resource: Hands-On Machine Learning by Aurelien Geron → https://lnkd.in/gxcjbJRp
𝟱. 𝗠𝗮𝗰𝗵𝗶𝗻𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗕𝗮𝘀𝗶𝗰𝘀 (𝟯-𝟰 𝗪𝗲𝗲𝗸𝘀) → Algorithms: Linear Regression, Logistic Regression, KNN, Decision Trees. → Tools: Scikit-learn. Resource: Andrew Ng’s Machine Learning Course → https://lnkd.in/gFwA_Gvq
𝟲. 𝗗𝗲𝗲𝗽 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 (𝟰-𝟲 𝗪𝗲𝗲𝗸𝘀) → Topics: Neural Networks, CNNs, RNNs. → Tools: TensorFlow, PyTorch. Resource: Deep Learning Specialization by Andrew Ng → https://lnkd.in/g4qZMHxd
𝟳. 𝗣𝗿𝗼𝗷𝗲𝗰𝘁𝘀 & 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗲 (𝗢𝗻𝗴𝗼𝗶𝗻𝗴) → Start small: Predictive modeling, image classification, NLP. → Platforms: Kaggle, DrivenData. Resource: Kaggle Competitions → kaggle.com/competitions
𝗧𝗶𝗽𝘀 𝗳𝗼𝗿 𝟮𝟬𝟮𝟱: → Leverage AI tools (ChatGPT, AutoML) for faster learning. → Focus on projects, not perfection. → Don’t just follow tutorials – build, break, and learn.
Machine Learning Book : https://drive.google.com/file/d/1aNOunm89etXOSlpIqi_mENGtWT6pRJjp/view?usp=sharing
400+ 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗥𝗲𝘀𝗼𝘂𝗿𝗰𝗲𝘀: https://lnkd.in/gv9yvfdd
𝗣𝗿𝗲𝗺𝗶𝘂𝗺 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗜𝗻𝘁𝗲𝗿𝘃𝗶𝗲𝘄 𝗥𝗲𝘀𝗼𝘂𝗿𝗰𝗲𝘀 : https://lnkd.in/gPrWQ8is
𝗣𝘆𝘁𝗵𝗼𝗻 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝗰𝗲 𝗟𝗶𝗯𝗿𝗮𝗿𝘆: https://lnkd.in/gHSDtsmA
45+ 𝗠𝗮𝘁𝗵𝗲𝗺𝗮𝘁𝗶𝗰𝘀 𝗕𝗼𝗼𝗸𝘀 𝗘𝘃𝗲𝗿𝘆 𝗗𝗮𝘁𝗮 𝗦𝗰𝗶𝗲𝗻𝘁𝗶𝘀𝘁 𝗡𝗲𝗲𝗱𝘀: https://lnkd.in/ghBXQfPc
Machine Learning Theory: https://www.youtube.com/watch?v=jGwO_UgTS7I&list=PLoROMvodv4rMiGQp3WXShtMGgzqpfVfbU&ab_channel=StanfordOnline
Introduction to DL : https://youtube.com/playlist?list=PLtBw6njQRU-rwp5__7C0oIVt26ZgjG9NI
Python: https://www.youtube.com/watch?v=rfscVS0vtbw&ab_channel=freeCodeCamp.org
Pandas: https://www.youtube.com/watch?v=2uvysYbKdjM&t=81s&ab_channel=KeithGalli
Numpy : https://www.youtube.com/watch?v=QUT1VHiLmmI&ab_channel=freeCodeCamp.org
Matplotlib : https://www.youtube.com/watch?v=3Xc3CA655Y4&ab_channel=freeCodeCamp.org
OOPS : https://www.youtube.com/watch?v=iLRZi0Gu8Go&ab_channel=freeCodeCamp.org
DSA : https://www.youtube.com/watch?v=pkYVOmU3MgA&ab_channel=freeCodeCamp.org
Data loading : https://www.youtube.com/watch?v=T23Bs75F7ZQ&ab_channel=freeCodeCamp.org
The best YouTube channels to learn AI from scratch
1] Andrej Karpathy – Deep learning, LLMs, intro to neural nets https://lnkd.in/evZk-rNk
2] 3Blue1Brown – Visual math that makes complex ideas intuitive https://lnkd.in/e5n9uzwn
3] Stanford Online (Andrew Ng – CS229 ML Course) https://lnkd.in/eXsE6CiG
4] Machine Learning Street Talk – Research deep dives & expert talks https://lnkd.in/eX2-mh39
5] StatQuest (Joshua Starmer) – ML + statistics made simple https://lnkd.in/ehiMxwUE
6] Serrano Academy (Luis Serrano) – Clear ML & AI lessons https://lnkd.in/eJsnz4NY
7] Jeremy Howard – Practical deep learning tutorials https://lnkd.in/ejnKrXYv
For any suggestions or resource contributions, reach out to:
Akhil Varanasi – Head of AI
Email: akhilvaranasi23@gmail.com
Happy Learning & Building!