Module 1. Introduction to AI & ML

Concepts:

• What is Artificial Intelligence
• What is Machine Learning
• Difference between AI, ML, Deep Learning
• Types of ML:
• Supervised
• Unsupervised
• Reinforcement Learning

Real-world examples:

• Netflix recommendation (ML)
• Self-driving cars (AI)
• Chatbots (AI + NLP)

Module 2. Python for AI/ML

Topics:

• Variables, Data Types
• Lists, Dictionaries, Sets
• Loops and Conditions
• Functions
• File Handling

Practical:

• Build simple programs (calculator, grading system)

Module 3. Mathematics for ML

Topics:

• Linear Algebra:
• Vectors
• Matrices
• Basic Calculus:
  Derivatives (concept only)
• Probability Basics:
• Events
• Conditional probability

Real-world:

• Matrix = image data
• Probability = prediction chances

Mini Project:

• Student Performance Analyzer (predict pass/fail using rules)

Module 1. NumPy

Topics:

• Arrays
• Mathematical operations
• Broadcasting

Module 2. Pandas

Topics:

• DataFrames
• Reading CSV/Excel
• Filtering, Sorting
• GroupBy

Module 3. Data Cleaning

Topics:

• Missing values
• Outliers
• Data formatting

Module 4. Statistics

Topics:

• Mean, Median, Mode
• Variance, Standard Deviation
• Normal Distribution

Module 5. Data Visualization

Tools:

• Matplotlib
• Seaborn

Charts:

• Bar, Line, Histogram, Heatmap

Project:

• Sales Data Analysis Dashboard

Module 1. ML Workflow

Topics:

• Data collection
• Data preprocessing
• Train-test split
• Model training
• Prediction

Module 2. Regression Algorithms

Topics:

• Linear Regression
• Multiple Regression

Working:

• Model finds relationship between input and output

Example:

• Predict house price using size and location

Module 3. Model Evaluation

Topics:

• MAE
• MSE
• RMSE
• R² Score

Module 4. Feature Engineering

Topics:

• Feature scaling
• Encoding categorical data

Project:

• House Price Prediction System

Module 1. Classification Algorithms

Topics:

• Logistic Regression
• K-Nearest Neighbors
• Support Vector Machine

Real-world:

• Spam detection (spam or not spam)

Module 2. Decision Trees

Topics:

• Tree structure
• Splitting criteria

Module 3. Ensemble Learning

Topics:

• Random Forest
• Gradient Boosting

Module 4. Model Optimization

Topics:

• Cross-validation
• Hyperparameter tuning

Module 5. Handling Imbalanced Data

Topics:

• Oversampling
• SMOTE concept

Project:

• Credit Card Fraud Detection System

Module 1. Neural Networks

Topics:

• Neuron concept
• Layers (input, hidden, output)
• Activation functions (ReLU, Sigmoid)

Module 2. Training Process

Topics:

• Forward propagation
• Backpropagation
• Loss functions

Module 3. Deep Learning Frameworks

Tools:

• TensorFlow
• PyTorch

Module 4. Computer Vision

Topics:

• Image representation
• Convolution Neural Networks (CNN)

Project:

• Image Classification System

Module 5. Natural Language Processing

Topics:

• Tokenization
• Stopwords removal
• Text vectorization

Module 6. NLP Models

Topics:

• Sentiment Analysis
• Text Classification

Module 7. Transformers (Introduction)

Tools:

• Hugging Face

Project:

• AI Chatbot or Sentiment Analyzer

Module 1. Model Deployment

Topics:

• API creation using Flask
• UI using Streamlit

Module 2. Cloud Basics

Topics:

• Amazon Web Services
• EC2 (server)
• S3 (storage)

Module 3. Version Control

Tools:

• Git
• GitHub

Module 4. End-to-End Pipeline

Steps:

• Data → Model → API → Deployment

Module 5. Capstone Project (Mandatory)

Students must build a complete system:

Options:

• Recommendation System
• Resume Screening AI
• Stock Price Predictor
• Healthcare Chatbot

Module 6. Placement Preparation

Topics:

• Resume building
• GitHub portfolio
• Mock interviews
• Case study discussion