Sem3

UNIT-I                                                                                                                       (15 Hours)

Introduction to Machine learning, essential concepts in Machine learning, Machine learning basics: Key terminology, Key tasks of machine learning, Types of learning, choosing the right algorithm, Steps in developing a machine learning application. Regression: Linear Regression, Best Fit Line in Linear Regression. Minimizing the Error: The Least Squares Method, Multiple Linear Regression, Evaluation Metrics for Linear Regression.

UNIT-II                                                                                                                      (15 Hours)

Classification: Supervised Learning, k-Nearest Neighbours classification algorithm, distance metrics, and the concept of K in KNN, binary and multi-label classification using KNN. Decision tree, entropy, Gini index, Information gain, Tree construction

UNIT-III                                                                                                                    (15 Hours)

Naïve Bayesian decision theory, Conditional probability, classifying with conditional probabilities, Document classification with naïve Bayes, classifying spam email with naïve Bayes. Support Vector Machines (SVM) - Introduction , goal of SVM, Working of SVM , Support Vectors, Hyperplane , Margin, SVM Kernels: Polynomial Kernel, Radial Basis Function (RBF) Kernel, Pros and Cons of SVM Classifiers.

UNIT-IV                                                                                                                    (15 Hours)

Recommender System: Introduction, Understanding Recommendation Systems, different types (collaborative filtering, content-based, hybrid). Content Based Filtering: content-based filtering methods, such as TF-IDF and cosine similarity, Collaborative Filtering: Explore collaborative filtering techniques, including user-based and item-based approaches, Issues in Recommendation Systems.