A curated collection of learning resources for Generative AI, Machine Learning, Agentic AI, and related topics.
Browse the interactive cheatsheet: viveknaskar.github.io/everything-ai-ml
Stay updated with the latest in AI — SavvyMonk Newsletter
- AI/ML Key Concepts
- AI/ML Building Blocks
- AI/ML Roadmap
- Generative AI – General
- Generative AI – Advanced
- Prompt Engineering
- RAG (Retrieval-Augmented Generation)
- Fine-tuning
- Frameworks
- Agentic AI
- MLOps and GenAIOps
- Security
- Google Cloud AI and ML
- AI Cost Optimization
- Adopting GenAI in Organizations
- AI Tools for Productivity
- Quantum Computing and PQC
- AI Augmented SDLC
- Coming Innovations in LLMs
- Courses
- Certifications
- Books
- Must-Read Research Papers
- Tools and Frameworks
- YouTube Channels
- Research Blogs
- Applied ML Blogs
- Communities
- Practice Problems
- Interview Preparation
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
- Deep Learning
- Natural Language Processing (NLP)
- Computer Vision
- Generative Adversarial Networks (GANs)
- Dimensionality Reduction
- Clustering Algorithms
- Bayesian Inference
- Time Series Analysis
- Self-Supervised Learning
Interactive Visualizations:
- MLU-Explain — Interactive visual explanations of core ML concepts
- CNN Explainer — In-browser interactive explainer for Convolutional Neural Networks
- Transformer Explainer — Interactive visualization of the Transformer architecture
- Mathematics for Machine Learning (UC Berkeley)
- Linear Algebra for ML – MIT OpenCourseWare
- Probability & Statistics – Stanford
- Calculus for Optimization – Khan Academy
- Python for ML – Coursera
- Optimization Techniques
- Data Preprocessing & Feature Engineering
- Model Evaluation & Metrics
- Regularization Techniques
- Loss Functions
- Activation Functions
- Hyperparameter Tuning
1. Learn Python and Core Libraries:
- Intro Python – Harvard CS50
- Advanced Python – Harvard AI with Python
- NumPy Quickstart
- Pandas Tutorial
- Matplotlib Tutorials
- Scikit-learn Tutorial
2. Build a Strong Math Foundation:
3. Learn ML Fundamentals:
4. Build Practical Experience:
- Practical Deep Learning for Coders – fast.ai
- Structured ML Projects – Coursera
- Build GPT from Scratch – Karpathy
5. Specialize:
- NLP Course – Hugging Face
- Deep RL Course – Hugging Face
- Computer Vision – Kaggle
- Deep Learning – CS231n Stanford
- Computer Vision, LLM, VLM Courses – PixelBank
6. Learn MLOps:
7. Read Research Papers:
- ArXiv — Preprint server for ML and AI research
Recommended Talks:
Visual Explainers:
- The Illustrated Transformer – Jay Alammar — Definitive visual guide to the Transformer architecture
- 3D Visualization of LLMs – Brendan Bycroft — Step-by-step 3D walkthrough of transformer execution
Learning Paths:
- Beginner: Introduction to Generative AI
- Intermediate: Gemini for Google Cloud
- Advanced: Generative AI for Developers
Coursera Courses:
- GenAI for Executives & Business Leaders: An Introduction
- GenAI for Execs & Business Leaders: Integration Strategy
- GenAI for Product R&D Teams
- GenAI for Product Managers
Gemini:
- Large Multimodal Model Prompting with Gemini – DeepLearning.AI
- Gemini for Application Developers – Coursera
- Gemini CLI: Code & Create with an Open-Source Agent
Google ADK:
- Building Live Voice Agents with Google's ADK – DeepLearning.AI
- Understand Google Cloud Agents – Coursera
Model Context Protocol (MCP):
- Prompt Engineering Guide — Comprehensive guide to prompt engineering techniques
- Prompt Engineering – OpenAI API
- Prompt Engineering – OpenAI Developer Docs — Official OpenAI developer documentation on prompt engineering best practices
- Prompt Engineering Overview – Anthropic — Official Anthropic guide to prompt engineering for Claude
- ChatGPT Prompt Engineering for Developers – DeepLearning.AI
- Google Prompting Essentials
- The Prompt Report: A Systematic Survey of Prompting Techniques — Comprehensive survey of 58 LLM prompting techniques with a unified taxonomy and vocabulary
- Anthropic Prompt Engineering Interactive Tutorial — Hands-on Jupyter notebook tutorial covering prompt engineering techniques for Claude
- OpenAI Tokenizer — Interactive tool to visualize how text is tokenized and count tokens for OpenAI models
- Building and Evaluating Advanced RAG Applications – DeepLearning.AI
- Knowledge Graphs for RAG – DeepLearning.AI
- Building Agentic RAG with LlamaIndex – DeepLearning.AI
- Finetuning Large Language Models – DeepLearning.AI
- Generative AI Advanced Fine-Tuning for LLMs – Coursera (IBM)
- Fine-tuning & RL for LLMs: Intro to Post-Training – DeepLearning.AI
LangChain:
- GitHub – langchain-ai/langchain
- LangChain Documentation
- LangChain for LLM Application Development – DeepLearning.AI
- LangChain: Chat with Your Data – DeepLearning.AI
- Functions, Tools and Agents with LangChain – DeepLearning.AI
LangGraph:
CrewAI:
- GitHub – crewAIInc/crewAI
- CrewAI Official Site
- Multi AI Agent Systems with crewAI – DeepLearning.AI
- Practical Multi AI Agents and Advanced Use Cases with crewAI
Google Agent Development Kit (ADK):
Agno (formerly Phidata):
- Agent Skills – Open Standard for Extending AI Agent Capabilities — Open standard for building reusable skills that extend AI agents across 30+ platforms including Claude, GitHub Copilot, and OpenAI Codex
- Introduction to Agent2Agent (A2A) Protocol – Google Cloud
- AI Agents Series – FuturMinds (YouTube Playlist)
- Evaluating AI Agents – DeepLearning.AI
- LLMs as Operating Systems: Agent Memory – DeepLearning.AI
- AI Agents in LangGraph – DeepLearning.AI
- AI Agentic Design Patterns with AutoGen – DeepLearning.AI
- Multi AI Agent Systems with crewAI – DeepLearning.AI
- Building Agentic RAG with LlamaIndex – DeepLearning.AI
- Event-Driven Agentic Document Workflows – DeepLearning.AI
- MLOps for Generative AI – Google Cloud Skill Boost
- GenAIOps: Operationalize Generative AI (YouTube)
- MLOps.org
- Full Stack Deep Learning
- Systems & Networking for AI Engineers – PixelBank
- OWASP Top 10 for Large Language Model Applications
- Google's Secure AI Framework (SAIF)
- The Dawn of Agentic AI in Security Operations – Google Cloud
Learning Paths on Cloud Skills Boost:
- Gemini for Google Cloud
- Beginner: Introduction to Generative AI
- Intermediate: Generative AI Labs with Gemini
- Deploy and Manage Generative AI Models
- Machine Learning Engineer Learning Path
- Build and Modernize Applications With Generative AI
- Integrate Generative AI Into Your Data Workflow
- Generate Smarter Generative AI Outputs
- Three Proven Strategies for Optimizing AI Costs – Google Cloud
- Reduce Cost and Improve Your AI Workloads – Google Cloud
- Vertex AI Pricing
- Generative AI for Executives and Business Leaders Specialization – Coursera (IBM)
- GenAI for Execs & Business Leaders: Integration Strategy – Coursera
- GenAI for Everyone – Coursera (DeepLearning.AI)
- Maximize Productivity with AI Tools – Coursera (Google)
- Google AI Professional Certificate – Coursera
- Microsoft 365 Copilot for Productivity – Coursera (Microsoft)
- Introduction to Post-Quantum Cryptography – edX (UMBC)
- Practical Introduction to Quantum-Safe Cryptography – IBM Quantum
- Generative AI for Software Development Specialization – DeepLearning.AI
- AI-Powered Software Development – Coursera
- GitHub Copilot Fundamentals – Microsoft Learn
- Google DeepMind Blog — Latest research and announcements from Google DeepMind
- Machine Learning by Andrew Ng (Coursera)
- AI For Everyone by Andrew Ng (Coursera)
- Deep Learning Specialization (Coursera)
- Machine Learning with Python (edX – IBM)
- Reinforcement Learning Specialization (Coursera)
- CS231n: CNNs for Visual Recognition (Stanford)
- RL Course by David Silver
- NLP with Deep Learning – Stanford CS224n
- Practical Deep Learning for Coders – fast.ai
- CV, LLM, VLM Courses – PixelBank
- AWS Certified Machine Learning Engineer – Associate
- AWS Certified AI Practitioner – Skill Builder
- Microsoft Certified: Azure AI Engineer Associate
- Stanford AI and Machine Learning Certificate
- Hands-On Large Language Models – Jay Alammar & Maarten Grootendorst — GitHub notebooks available
- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
- AI Engineering: Building Applications with Foundational Models
- Introduction to Machine Learning Interviews – Chip Huyen
- Designing Data-Intensive Applications
- Designing Machine Learning Systems
- Deep Learning (Goodfellow, Bengio, Courville)
- Patterns, Predictions, and Actions – Hardt & Recht — Free textbook covering supervised learning, deep learning, causal inference, and RL
- Attention Is All You Need (Google)
- Language Models are Few-Shot Learners – GPT-3 (OpenAI) — Introduces GPT-3, a 175B parameter model demonstrating strong few-shot learning across NLP tasks
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (Google) — Introduces chain-of-thought prompting, showing intermediate reasoning steps significantly improve LLM performance on complex tasks
- DeepSeek R1: Incentivizing Reasoning Capability in LLMs
- Monolith: Real Time Recommendation System (TikTok/ByteDance)
- BERT: Pre-training of Deep Bidirectional Transformers
- Understanding Deep Learning Requires Rethinking Generalization
- Playing Atari with Deep Reinforcement Learning
- Distilling the Knowledge in a Neural Network
- OpenAI Key Papers in Deep RL
Research Discovery Tools:
- Ai2 Asta — Agentic research assistant by Allen Institute for AI; discovers and synthesizes literature across 200M+ papers
- PyTorch
- TensorFlow
- TensorFlow Playground — Browser-based neural network experimentation tool
- Scikit-Learn
- XGBoost
- Keras
- Whisper – OpenAI
- Can I Run AI? — Check if your hardware can run AI models locally
- OpenAI Blog
- Google DeepMind
- Google Research
- Apple ML Research
- Amazon Science
- Microsoft AI
- Meta AI Blog
- AWS Machine Learning Blog
- NVIDIA Deep Learning Blog
- AirBnB Engineering – AI & ML
- Spotify Engineering
- Uber Engineering – AI
- Netflix Tech Blog
- Google AI Blog
Easy:
Medium:
- Single Neuron
- K-Means Clustering
- Predicting Loan Default Risk – Kaggle
- Sentiment Analysis on Movie Reviews – Kaggle
Hard:
- Decision Tree Learning
- Implement a Simple RNN with Backpropagation
- GANs for Image Synthesis – Kaggle
- Introduction to Machine Learning Interviews – Chip Huyen
- ML Interviews MVP – GitHub
- Designing Machine Learning Systems
- ML System Design: 650 Case Studies – GitHub — Real-world ML use cases from 100+ companies including Netflix, Airbnb, and Uber
- AI Engineering from Scratch – GitHub
- ML Coding Questions – PixelBank
Feel free to open a PR if you have useful resources to add.
The resource list above is generated from a single source of truth:
website/src/data/resources.ts. Edit that file,
then regenerate this README so the two stay in sync:
cd website
npm install # first time only
npm run gen:readmeSee CONTRIBUTING.md for details.
This repository is for educational purposes. All linked content belongs to their respective owners.