SEM - III

The Artificial Intelligence and Machine Learning course provides students with a comprehensive foundation in AI concepts, problem-solving techniques, machine learning principles, supervised learning algorithms, and neural networks. It begins with an introduction to Artificial Intelligence, covering its definition, scope, characteristics of AI problems, State Space Representation, Production Systems, and criteria for evaluating successful AI solutions. Students then learn important Search Techniques such as Breadth First Search (BFS), Depth First Search (DFS), Hill Climbing, Best First Search, and Constraint Satisfaction Problems (CSP) for solving AI-based problems. The course introduces Machine Learning, including its definition, need, types such as Supervised, Unsupervised, and Reinforcement Learning, applications of ML, training and testing concepts, and overfitting and underfitting. Students further study major Supervised Learning Algorithms, including Linear Regression, Logistic Regression, Decision Trees, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest, and Naïve Bayes Classifier. The course concludes with Neural Networks, covering the Perceptron, Multi-layer Neural Networks, and the Backpropagation Algorithm, providing students with a foundation for understanding how intelligent systems learn patterns from data and make predictions or decisions