Manipal Open Source Society - AI Resources

Repository for AI Learning & Development Resources

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.

---

Contents

• 📚 Tutorials & Guides
• 🧑‍💻 Coding Practice & Projects
• 📊 Research Papers & Articles
• 🛠️ Tools & Libraries
• 🎥 Video Lectures & Workshops
• 💡 AI Concepts & Notes

---

Roadmap :

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.

That’s the roadmap I’d take – no fluff, just results.

📚 Tutorials & Guides

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

🎥 Video Lectures

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

𝐇𝐞𝐫𝐞 𝐚𝐫𝐞 𝟐𝟎 𝐘𝐨𝐮𝐓𝐮𝐛𝐞 𝐜𝐡𝐚𝐧𝐧𝐞𝐥𝐬 𝐭𝐡𝐚𝐭 𝐦𝐚𝐤𝐞 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 𝐀𝐈 𝐬𝐢𝐦𝐩𝐥𝐞 & 𝐬𝐭𝐫𝐮𝐜𝐭𝐮𝐫𝐞𝐝:

1. 3Blue1Brown: Understand complex math behind AI visually and intuitively. Link: https://lnkd.in/edegfEEv

2. Andrej Karpathy : Deep, practical AI lectures explained clearly. Link: https://lnkd.in/eay7TU2a

3. Lex Fridman : Conversations with leading AI researchers and innovators. Link: https://lnkd.in/ebbtpsww

4. StatQuest (Josh Starmer): Makes ML concepts fun with humor and clarity. Link: https://lnkd.in/eqTeYjMT

5. Jeremy Howard : Practical deep learning with hands-on coding examples. Link: https://lnkd.in/e_vHAu84

6. Two Minute Papers: Summaries of the latest AI papers in minutes. Link: https://lnkd.in/eyBhZC9p

7. DeepLearning.AI: Structured AI learning from Andrew Ng. Link: https://lnkd.in/e62uRF2g

8. Machine Learning Street Talk (MLST): Insightful debates and interviews. Link: https://lnkd.in/eUwV47cn

9. freeCodeCamp: Free AI and ML tutorials with certification paths. Link: https://lnkd.in/eUn2JUiM

10. Sentdex : Python-based machine learning and data projects. Link: https://lnkd.in/e-dCBfas

11. Data School : Simple ML and data analysis concepts for beginners. Link: https://lnkd.in/egtSHRy8

12. Codebasics: Real-world ML use cases and career-focused projects. Link: https://lnkd.in/ez2NmfVd

13. Siraj Raval : Story-driven tutorials combining creativity and AI. Link: https://lnkd.in/ehJf3jzR

14. Google Cloud Tech: Learn how to deploy and manage AI models. Link: https://lnkd.in/euJTVeyM

15. Serrano Academy: Step-by-step tutorials on ML, DL, and AI tools. Link: https://lnkd.in/eSzJJJWY

16. Tina Huang : Smart AI learning strategies and productivity tips. Link: https://lnkd.in/exwv6q7i

17. Matt Wolfe : Quick updates on new AI tools and technologies. Link: https://lnkd.in/eiVMeZj3

18. AI Explained: Deep dives into AI ethics, models, and progress. Link: https://lnkd.in/etfCYhMq

19. The AI Advantage: Practical ways AI is transforming business productivity. Link: https://lnkd.in/egyKfySP

20. Hamel Husain : Advanced insights into LLMs, RAG, and model fine-tuning. Link: https://lnkd.in/eSgQMg_d

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

---

𝗖𝗼𝗿𝗲 𝗖𝗼𝗻𝗰𝗲𝗽𝘁𝘀:

• CI/CD (Continuous Integration & Deployment) – https://lnkd.in/dNdq9FSn
• Model Versioning & Registry – https://lnkd.in/d-QU637Z
• Experiment Tracking (MLflow / W&B) – https://lnkd.in/deFrPyHU
• Data Version Control (DVC) – https://lnkd.in/d5VQazN9
• Monitoring & Drift Detection – https://lnkd.in/dYwu-q2m

𝗠𝗟𝗢𝗽𝘀 𝗕𝘂𝗶𝗹𝗱𝗶𝗻𝗴 𝗕𝗹𝗼𝗰𝗸𝘀:

• Data Pipeline (ETL / ELT) – https://lnkd.in/dhnTfFHP
• Feature Store (Feast / Tecton) – https://lnkd.in/dHJJ36a4
• Model Packaging (Docker / ONNX) - https://lnkd.in/dxGvWJ4w
• Deployment (Batch / Real-Time / Edge) – https://lnkd.in/du7ej8p2
• Orchestration (Airflow / Prefect / Kubeflow) – https://lnkd.in/dDCrHszG
• Observability (Prometheus / Grafana) – https://lnkd.in/dYw_QQtA

𝗦𝘆𝘀𝘁𝗲𝗺 𝗗𝗲𝘀𝗶𝗴𝗻 𝗣𝗮𝘁𝘁𝗲𝗿𝗻𝘀:

• Batch vs Online Inference – https://lnkd.in/dkE4RZ23
• Shadow / Canary / Blue-Green Deployments –https://lnkd.in/dZedEeWm
• Retraining & Continuous Learning – https://lnkd.in/dEKNbTT7
• Feedback Loops & Drift Correction – https://lnkd.in/drRXMTAd

---

AI Agents

📹 Videos:

1. LLM Introduction: https://www.youtube.com/watch?v=zjkBMFhNj_g
2. LLMs from Scratch: https://www.youtube.com/watch?v=9vM4p9NN0Ts
3. Agentic AI Overview (Stanford): https://www.youtube.com/watch?v=kJLiOGle3Lw
4. Building and Evaluating Agents: https://www.youtube.com/watch?v=d5EltXhbcfA
5. Building Effective Agents: https://www.youtube.com/watch?v=D7_ipDqhtwk
6. Building Agents with MCP: https://www.youtube.com/watch?v=kQmXtrmQ5Zg
7. Building an Agent from Scratch: https://www.youtube.com/watch?v=xzXdLRUyjUg
8. Philo Agents: https://www.youtube.com/playlist?list=PLacQJwuclt_sV-tfZmpT1Ov6jldHl30NR

🗂️ Repos

1. GenAI Agents: https://github.com/nirdiamant/GenAI_Agents
2. Microsoft's AI Agents for Beginners: https://github.com/microsoft/ai-agents-for-beginners
3. Prompt Engineering Guide: https://lnkd.in/gJjGbxQr
4. Hands-On Large Language Models: https://lnkd.in/dxaVF86w
5. AI Agents for Beginners: https://github.com/microsoft/ai-agents-for-beginners
6. GenAI Agentshttps://lnkd.in/dEt72MEy
7. Made with ML: https://lnkd.in/d2dMACMj
8. Hands-On AI Engineering:https://github.com/Sumanth077/Hands-On-AI-Engineering
9. Awesome Generative AI Guide: https://lnkd.in/dJ8gxp3a
10. Designing Machine Learning Systems: https://lnkd.in/dEx8sQJK
11. Machine Learning for Beginners from Microsoft: https://lnkd.in/dBj3BAEY
12. LLM Course: https://github.com/mlabonne/llm-course

🗺️ Guides

1. Google's Agent Whitepaper: https://lnkd.in/gFvCfbSN
2. Google's Agent Companion: https://lnkd.in/gfmCrgAH
3. Building Effective Agents by Anthropic: https://lnkd.in/gRWKANS4.
4. Claude Code Best Agentic Coding practices: https://lnkd.in/gs99zyCf
5. OpenAI's Practical Guide to Building Agents: https://lnkd.in/guRfXsFK

📚Books:

1. Understanding Deep Learning: https://udlbook.github.io/udlbook/
2. Building an LLM from Scratch: https://lnkd.in/g2YGbnWS
3. The LLM Engineering Handbook: https://lnkd.in/gWUT2EXe
4. AI Agents: The Definitive Guide - Nicole Koenigstein: https://lnkd.in/dJ9wFNMD
5. Building Applications with AI Agents - Michael Albada: https://lnkd.in/dSs8srk5
6. AI Agents with MCP - Kyle Stratis: https://lnkd.in/dR22bEiZ
7. AI Engineering: https://www.oreilly.com/library/view/ai-engineering/9781098166298/

📜 Papers

1. ReAct: https://lnkd.in/gRBH3ZRq
2. Generative Agents: https://lnkd.in/gsDCUsWm.
3. Toolformer: https://lnkd.in/gyzrege6
4. Chain-of-Thought Prompting: https://lnkd.in/gaK5CXzD.
5. Tree of Thoughts: https://lnkd.in/gRJdv_iU.
6. Reflexion: https://lnkd.in/gGFMgjUj
7. Retrieval-Augmented Generation Survey: https://lnkd.in/gGUqkkyR.

🧑‍🏫 Courses:

1. HuggingFace's Agent Course: https://lnkd.in/gmTftTXV
2. MCP with Anthropic: https://lnkd.in/geffcwdq
3. Building Vector Databases with Pinecone: https://lnkd.in/gCS4sd7Y
4. Vector Databases from Embeddings to Apps: https://lnkd.in/gm9HR6_2
5. Agent Memory: https://lnkd.in/gNFpC542
6. Building and Evaluating RAG apps: https://lnkd.in/g2qC9-mh
7. Building Browser Agents: https://lnkd.in/gsMmCifQ
8. LLMOps: https://lnkd.in/g7bHU37w
9. Evaluating AI Agents: https://lnkd.in/gHJtwF5s
10. Computer Use with Anthropic: https://lnkd.in/gMUWg7Fa
11. Multi-Agent Use: https://lnkd.in/gU9DY9kj
12. Improving LLM Accuracy: https://lnkd.in/gsE-4FvY
13. Agent Design Patterns: https://lnkd.in/gzKvx5A4
14. Multi Agent Systems: https://lnkd.in/gUayts9s

📩 Newsletters

1. Gradient Ascent: https://lnkd.in/gZbZAeQW
2. DecodingML by Paul: https://lnkd.in/gpZPgk7J
3. Deep (Learning) Focus by Cameron: https://lnkd.in/gTUNcUVE
4. NeoSage by Shivani: https://blog.neosage.io/
5. Jam with AI by Shirin and Shantanu: https://lnkd.in/gQXJzuV8
6. Data Hustle by Sai: https://lnkd.in/gZpdTTYD

---

Contact

For any suggestions or resource contributions, reach out to:
Akhil Varanasi – Head of AI
Email: akhilvaranasi23@gmail.com

---

Happy Learning & Building!