Foundation Course on AI/ ML

Course Title: Foundations of Artificial Intelligence and Machine Learning

📘 Unit-wise Structure (5 Units × 20 marks)

Unit 1: Introduction to Artificial Intelligence........................  Weightage: 20 marks

• Definition, history, and evolution of AI
• Types of AI (Narrow, General, Strong, Weak)
• Applications of AI across disciplines (Healthcare, Finance, Education, Libraries, etc.)
• Foundations of AI: Logic, Search, Knowledge Representation
• Ethical and social issues in AI (bias, transparency, job automation)
• Introduction to intelligent agents and environments

Unit 2: Fundamentals of Machine Learning.  .  .  .  .  .  .  .  .  .  .  .  Weightage: 20 markz

• Difference between AI and ML
• ML paradigms: Supervised, Unsupervised, and Reinforcement Learning
• Model training process (training, validation, testing)
• Bias-variance tradeoff
• Underfitting vs. overfitting
• ML tools and frameworks (e.g., Scikit-learn, TensorFlow – brief intro)

Unit 3: Supervised Learning Algorithms.  .  .  .  .  .  .  .  .  .  .  .  Weightage: 20 marks

• Regression (Linear and Logistic)
• Classification (k-NN, Decision Trees, Random Forests)
• Performance metrics: Accuracy, Precision, Recall, F1 Score, Confusion Matrix
• Use cases: Email spam detection, credit risk analysis

Unit 4: Unsupervised Learning and Neural Networks .  .  .  .  .  .   Weightage: 20 marks

• Clustering (k-Means, Hierarchical)
• Dimensionality Reduction (PCA, t-SNE – brief overview)
• Basics of Artificial Neural Networks (Perceptron, MLP)
• Introduction to Deep Learning (only conceptual)
• Applications: Image classification, customer segmentation

Unit 5: Practical Applications and Future Trends.                 .Weightage: 20 marks

• Real-world case studies (AI in healthcare, NLP in chatbots, recommendation systems)
• Basics of Natural Language Processing (tokenization, sentiment analysis)
• Reinforcement learning concepts (agent, environment, rewards – conceptual only)
• Recent trends: Generative AI (ChatGPT, DALL·E – overview), Explainable AI, AI and ethics
• Hands-on: Outline of 1–2 beginner ML projects (e.g., Titanic dataset, Iris classification)