Foundation of Artificial and Machine Learning

Foundations of Artificial Intelligence What is AI? History of AI, Foundations of AI. Intelligent Agents: Rational agents, Agent architectures, Environment types. Problem Solving by Search: State-space graphs. Uninformed search strategies, Informed Search: Greedy Best-First Search, A* Search, Hill Climbing

Knowledge Representation First order logic – Knowledge Representation, Syntax and semantics in first order logic, Knowledge engineering in first order logic, Inference in First order logic. Prepositional versus first order logic, Unification and lifting, Forward chaining and Backward Chaining, Ontological Engineering.

Introduction to Artificial Neural Network Foundations: Biological neurons vs. Artificial neurons, The Perceptron model, limitations of the single-layer perceptron. Network Architecture: Multi-Layer Perceptron (MLP) and Feedforward Neural Networks. Activation Functions: Linear, Sigmoid, Tanh, Softmax, and ReLU. Training the Network-The Backpropagation algorithm, calculating gradients, Loss functions, updating weights using Gradient Descent.

Supervised Learning Introduction to Machine learning, Learning Strategies. Classification Algorithms: Logistic Regression, K-Nearest Neighbors, Decision Trees, Support Vector Machines and Naive Bayes Classifier. Ensemble Learning: Introduction to Bagging and Boosting, Random Forests. Evaluation Metrics: Confusion Matrix, Accuracy, Precision, Recall, F1-Score, ROC-AUC Curve.

Unsupervised Learning Supervised vs. Unsupervised Learning, Clustering Algorithms, K- Means Clustering Hierarchical Clustering, DBSCAN etc., Dimensionality Reduction: The Curse of Dimensionality, Introduction to Principal Component Analysis.