Week 1: AI & ML Fundamentals

Goal: Build strong conceptual foundations.

Topics

• What is Artificial Intelligence vs Machine Learning vs Deep Learning

  Types of ML:

  • Supervised Learning

  • Unsupervised Learning

  • Reinforcement Learning

• Real-world AI/ML use cases

  ML workflow:

  • Data → Features → Model → Training → Evaluation → Deployment

• Introduction to Python for ML

• Basic Python syntax (variables, loops, functions)

• Intro to Jupyter Notebooks

Hands-on

• Python basics exercises

• Simple data manipulation using NumPy

Week 2: Data & Classical Machine Learning

Goal: Learn how data drives ML models.

Topics

• Data types (structured vs unstructured)

  Data preprocessing:

  • Missing values

  • Encoding categorical data

  • Feature scaling

• Exploratory Data Analysis (EDA)

  Supervised Learning:

  • Linear Regression

  • Logistic Regression

  • k-Nearest Neighbors (k-NN)

  Model evaluation:

  • Train/Test split

  • Accuracy, Precision, Recall

Hands-on

• Data analysis with pandas

• Build ML models using scikit-learn

• Predict house prices or classify emails (spam/ham)

Week 3: Unsupervised Learning & Model Improvement

Goal: Understand patterns without labels and improve models.

Topics

Unsupervised Learning:

• Clustering (K-Means)

• Dimensionality Reduction (PCA)

• Overfitting vs Underfitting

• Bias–Variance tradeoff

• Hyperparameter tuning

• Cross-validation

• Introduction to pipelines

Hands-on

• Customer segmentation using K-Means

• Improve model accuracy with tuning

• Visualize clusters and PCA components

Week 4: Neural Networks & AI Awareness

Goal: Get introduced to Deep Learning and responsible AI.

Topics

• Biological vs Artificial Neurons

  Neural Network basics:

  • Perceptron

  • Activation functions

  • Loss functions

• Intro to Deep Learning frameworks

  Ethical AI:

  • Bias in models

  • Data privacy

  • Explainability

• AI project lifecycle overview

Hands-on

• Build a simple neural network (from scratch or using a framework)

  Mini-project:

  • Image classification (basic)

  • Prediction or clustering task

• Model presentation & interpretation

Final Outcomes

By the end of 4 weeks, learners will be able to:

• Explain core AI/ML concepts confidently

• Prepare and analyze datasets

• Train and evaluate ML models

• Understand neural networks at a beginner level

• Build an end-to-end ML mini project