AI & Machine Learning — From Basic to Advance (24 Weeks)

Practical, project-driven curriculum with weekly assignments and mini-projects to build production-ready machine learning competencies.

WEEK 1 — Introduction to AI & ML

• AI, ML, DL & Data Science overview
• Types of ML
• Applications & environment setup

WEEK 2 — Python Programming for ML

• Python basics, data structures
• Functions & file handling

WEEK 3 — NumPy & Pandas

• Arrays, slicing
• Data cleaning & analysis

WEEK 4 — Data Visualization

• Matplotlib & Seaborn
• Charts & dashboards

WEEK 5 — Math & Statistics

• Statistics, probability
• Hypothesis testing

WEEK 6 — ML Fundamentals

• ML workflow
• Linear regression

WEEK 7 — Regression Models

• Linear, Polynomial, Ridge & Lasso

WEEK 8 — Classification Models

• KNN, Decision Tree
• Random Forest

WEEK 9 — Feature Engineering

• Encoding & scaling

WEEK 10 — Model Optimization

• Cross-validation
• Hyperparameter tuning

WEEK 11 — Unsupervised Learning

• K-Means
• PCA

WEEK 12 — Ensemble Techniques

• Bagging & Boosting

WEEK 13 — Neural Network Basics

• Neuron, activation functions

WEEK 14 — ANN with TensorFlow

• ANN architectures

WEEK 15 — CNN

• Image classification

WEEK 16 — Transfer Learning

• Pre-trained models

WEEK 17 — NLP Basics

• Text preprocessing

WEEK 18 — Sentiment Analysis

• Text classification

WEEK 19 — Advanced NLP

• RNN, LSTM, Transformers

WEEK 20 — Reinforcement Learning

• Q-learning & DQN

WEEK 21 — Model Deployment

• Flask, FastAPI, Streamlit

WEEK 22 — MLOps

• Git, MLflow, Docker

WEEKS 23–24 — Capstone Project

• End-to-end real-world project
• Deployment & presentation