Modern AI Curriculum
A complete, step-by-step roadmap from Machine Learning foundations to Deep Learning, Generative AI, LLMs, and Production AI Agents.
Personal Learning Progress
Begin Your AI Journey 🧭
Select any topic to start reading, or follow the curated order.
0%(0/167 Lessons)
Overall Course Completion0%
Explore by Learning Track
Filter modules by your learning goal or view the complete curriculum roadmap.
All curriculum· 17 modules, 167 tutorial lessons + 12 project handbooks
Explore all 17 modules and 167 tutorials across the complete curriculum.
1. Foundations
0/70%
2. Python & ML Libraries
0/40%
3. Data Preprocessing & Feature Engineering
0/80%
4. Supervised Learning
0/120%
5. Ensemble Learning
0/60%
6. Unsupervised Learning
0/70%
7. Model Evaluation & Optimization
0/80%
8. Time Series & Forecasting
0/40%
9. Advanced Learning Paradigms
0/40%
10. Deep Learning
0/240%
- Deep Learning Basics and Model Types
- How Neural Networks Learn
- Essential Math for Neural Networks
- Activation Functions
- Tensors, Frameworks & GPUs
- Loss Functions: MSE, MAE and Cross-Entropy
- Backpropagation and Automatic Differentiation
- Training and Debugging a Neural Network
- Optimizers and Learning-Rate Scheduling
- Initialization, Normalization and Stable Gradients
- Regularization and Generalization
- Data Augmentation
- CNNs and Image Classification
- CNN Architectures: AlexNet to ResNet
- Object Detection, Segmentation and Grad-CAM
- Vision Transformers
- RNNs, LSTMs and GRUs
- Sequence-to-Sequence Models and Attention
- Transformers for Deep Learning
- Autoencoders and Their Variants
- Transfer Learning and Fine-Tuning
- Self-Supervised and Few-Shot Learning
- Graph Neural Networks
- Saving, Loading & Deploying Deep Models
11. Advanced Deep Learning Topics
0/30%
12. Generative AI
0/170%
- Module 1 — Foundations
- What Is Generative AI?
- Generative vs Discriminative Models
- How Generative Models Learn and Generate New Data
- Module 2 — Core Generative Model Families
- Variational Autoencoders for Generation
- Generative Adversarial Networks (GANs)
- Diffusion Models
- Latent Diffusion and Stable Diffusion Architecture
- Controlling Diffusion Models
- Fine-Tuning Image Generation Models
- Module 3 — Beyond Images
- Multimodal Generative AI
- Audio, Speech, Music and Video Generation
- Synthetic Data Generation
- Module 4 — Evaluation, Responsibility and Selection
- Evaluating Generative Models
- Responsible Generative AI
- Choosing the Right Generative Model
- Module 5 — Applications and Production
- Building Generative AI Applications
- Deploying Generative AI Applications
13. Large Language Models
0/160%
- What Are Large Language Models? From N-Grams to Modern LLMs
- Tokens, Embeddings & Context Windows
- Transformer Architecture & LLM Model Families
- How LLMs Generate Text: Next-Token Prediction & Decoding
- Prompt Engineering, Structured Outputs & Function Calling
- How LLMs Are Trained: Data, Pretraining, Scale & Compute
- Fine-Tuning & Alignment: SFT, RLHF and LoRA
- Retrieval-Augmented Generation (RAG)
- Semantic Search with Embeddings
- Vector Databases
- Advanced RAG: Chunking, Retrieval, Reranking & Evaluation
- Evaluating LLMs, Benchmarks & Model Selection
- Hallucinations, Guardrails & Responsible LLM Use
- Reasoning Models & Test-Time Compute
- Efficient LLM Inference & Serving
- LLMOps & Building Production LLM Applications
14. Agentic AI
0/160%
- What Is Agentic AI? Agents, Workflows & Types
- Tool Calling & Reliable Tool Design
- Build a Simple AI Agent End-to-End
- Planning, ReAct & Reflection
- Context Engineering for Agents
- Memory in AI Agents: Short-Term, Long-Term & Persistence
- Agent Workflows, State Machines & Graphs
- Durable & Long-Running Agents with Human-in-the-Loop
- Agentic RAG
- Multi-Agent Systems, Handoffs & Agent Communication
- Model Context Protocol (MCP) & Agent Interoperability
- Agent Frameworks: LangGraph, CrewAI & AutoGen
- Browser, Computer-Use & Code-Executing Agents
- Agent Security, Guardrails & Failure Recovery
- Evaluating Agents: Task Success, Safety, Trajectories & Benchmarks
- Agent Observability, Cost, Latency & Deployment
Hands-on builds & practical lessons
15. Project Handbooks & Tutorial Lessons
Tutorial Lessons Tracked:0/8 completed (0%)
0%
This module features two distinct learning formats: 12 full practical project handbooks (complete runnable applications built from an empty folder) and 8 curriculum tutorial lessons (core lessons teaching project problem-framing, architectures, baselines, and production readiness).
Practical Project Handbooks
12 BuildsFull reference implementations with raw data, pipelines, Streamlit UI, tests, and starter downloads. Available independently of lesson progress.
Titanic Survival Predictor
Beginner/projects/titanic-survival
House Price Predictor
Beginner/projects/house-price
Credit Card Fraud Detector
Intermediate/projects/credit-card-fraud
Customer Segmentation
Beginner/projects/customer-segmentation
Retail Sales Forecaster
Intermediate/projects/retail-forecasting
Movie Recommendation System
Intermediate/projects/movie-recommender
Disaster Tweet Detector
Intermediate/projects/disaster-tweets
Handwritten Digit Recognizer
Intermediate/projects/digit-recognizer
AI Content Creator
Intermediate/projects/ai-content-creator
PDF RAG Assistant
Intermediate/projects/pdf-rag
AI Research Assistant
Advanced/projects/ai-research-assistant
Model to Production
Advanced/projects/model-to-production
Need starter ZIPs & walkthroughs?View All Handbooks Directory
Curriculum Tutorial Lessons
8 Tracked LessonsSequential curriculum lessons teaching methodology, validation, and error analysis. Tracked in your learning progress.
- Customer Churn Prediction — End-to-End ML Project↳ Production Serving Build:Model to Production
- Credit Risk Prediction with Explainable ML↳ Related Financial Risk Build:Credit Card Fraud Detector
- Image Classification with Transfer Learning↳ Practical Build:Handwritten Digit Recognizer
- Build a Generative AI Application End-to-End↳ Practical Build:AI Content Creator
- Build a Document Q&A System with RAG↳ Practical Build:PDF RAG Assistant
- Build an AI Agent with Tools & Memory↳ Practical Build:AI Research Assistant
- Build a Multi-Agent Research Assistant↳ Practical Build:AI Research Assistant
16. AI Engineering & MLOps
0/80%
- AI Engineering & MLOps: From Notebook to Production
- Production Data, Feature & ML Pipelines
- Experiment Tracking, Reproducibility, Lineage & Model Registry
- Batch, Online & Streaming Inference Architectures
- Testing, CI/CD & Continuous Training for ML
- ML Monitoring, Data Drift & Model Decay
- Production AI Reliability, Security, Cost & Governance
- End-to-End ML/AI System Design
17. Career & Interview Preparation
0/150%
- Career Roadmaps
- Choose Your AI & Data Career
- Machine Learning Engineer Roadmap
- AI Engineer Roadmap
- Generative AI / LLM Engineer Roadmap
- Data Scientist Roadmap
- Interview Preparation
- How AI/ML Interviews Work & How to Prepare
- ML, Statistics & Model Evaluation Interview Questions
- Deep Learning Interview Questions
- Generative AI, LLM & RAG Interview Questions
- Agentic AI Interview Questions
- Python Coding for AI/ML Interviews
- SQL for AI/Data Interviews
- ML & AI System Design Interviews
- MLOps, Production & Debugging Interview Scenarios
- Project Deep-Dive, Resume & Behavioral Interviews