Standard ML courses stop at basic classification and rule-based chatbots. We have upgraded this syllabus to include what tech companies actually hire for today:

• Large Language Models (LLMs): Moving beyond using ChatGPT as a tool, to actually building with LLM APIs (OpenAI, Hugging Face).
• Retrieval-Augmented Generation (RAG): Teaching students how to connect AI to custom data using Vector Databases.
• AI Agents & LangChain: Building autonomous systems, not just simple scripts.
• Model Deployment: Teaching students how to build a web interface for their AI using Streamlit, rather than leaving models stuck in a Jupyter Notebook.

Course Curriculum

Module 1: Python Programming Foundations (Days 1–5)

• Day 1: Introduction to AI & ML | Real-world applications | Setting up Google Colab.
• Day 2: Python Basics | Variables, Data Types, I/O, Arithmetic & Logical Operations.
• Day 3: Control Flow | Conditional Statements (if/else) and Loops (for/while).
• Day 4: Data Structures & Functions | Lists, Tuples, Dictionaries, and writing reusable functions.
• Day 5: String Operations & Error Handling | Debugging | Assignment: Basic Python Scripting.

Module 2: Data Engineering & Visualization (Days 6–10)

• Day 6: Numerical Computing with NumPy | Arrays, indexing, matrix reshaping.
• Day 7: Data Manipulation with Pandas | DataFrames, importing CSVs, basic exploratory data analysis.
• Day 8: Data Visualization | Matplotlib & Seaborn | Bar graphs, line plots, histograms, and heatmaps.
• Day 9: Applied Statistics for ML | Mean, median, standard deviation, and probability basics.
• Day 10: Data Preprocessing | Handling null values, encoding, and scaling | Quiz + Real Dataset Cleaning Assignment.

Module 3: Core Machine Learning Algorithms (Days 11–15)

• Day 11: Introduction to ML | Supervised vs. Unsupervised Learning | The ML Workflow.
• Day 12: Linear Regression | Theory, mathematics, and hands-on simple prediction modeling.
• Day 13: Classification Models | K-Nearest Neighbors (KNN) | Understanding the Confusion Matrix, Precision, and Recall.
• Day 14: Decision Trees | Theory, Gini impurity, and scikit-learn walkthrough.
• Day 15: Model Evaluation & Hyperparameter Tuning | Assignment: Build and optimize your own prediction model.

Module 4: NLP & Generative AI Architecture (Days 16–21) (Modernized)

• Day 16: Natural Language Processing (NLP) Basics | Tokenization, stopwords, TF-IDF.
• Day 17: Traditional Sentiment Analysis | Building a text classifier using Scikit-Learn.
• Day 18: Advanced Prompt Engineering & LLM APIs | Programmatic access to ChatGPT/Gemini models.
• Day 19: Building Modern Chatbots | Moving beyond rule-based logic to LLM-driven conversational AI.
• Day 20: [NEW] Intro to RAG & Vector Databases | How to give an LLM “memory” and custom data.
• Day 21: [NEW] AI Application Deployment | Wrapping ML models and Chatbots in web UI using Streamlit.

Module 5: Capstone Project & Career Prep (Days 22–30)

• Day 22: Project Brainstorming & Architecture | Team formation.
• Days 23–26: Capstone Project Development | Options include: RAG-powered Document QA, Real-time Spam Detector, Customer Churn Predictor, or an LLM-based Study Assistant.
• Day 27: Project Finalization, Bug Testing, and Presentation Prep.
• Days 28–29: Final Project Presentations | Live demos, Q&A, and peer feedback.
• Day 30: The AI Career Roadmap | Building a portfolio, understanding AI Ethics & Safety, and Course Review.