road-map.md

Modules - A Roadmap to learn Machine Learning 📂

Module 1: Introduction and Concept Learning

Types of Machine Learning - Examples of Machine Learning Problems - Models and Data - Characteristics of Machine learning model - Concept Learning: Theory of Generalization - Version Spaces and the Candidate Elimination Algorithm.

Module 2: Feature Engineering

Data Collection - Preprocessing: Data Cleaning - Data Transformation: Normalization, Binning, Discretization - Scaling - Dimensionality Reduction - Automatic Feature Selection and Extraction, (Data Preprocessing using Population Data) Feature extraction.

Module 3: Linear, Nonlinear and Probabilistic Models

Linear and Nonlinear Models: Binary and Multiclass classification - Univariate Linear Regression - Multivariate Linear Regression (Predicting Solar Radiation using Regression) - Logistic Regression - Perceptron (Logistic Regression using Insurance Fraud Detection), Multiple Layer Perceptron - Kernalized Support Vector Machines (SVM) - (Character recognition using Classification) - Ensemble Learning - Bagging and Boosting - Random Forest - Probabilistic models: Naïve Bayes Classifier.

Module 4: Distance Based Models

Distance Based Models: - K-Nearest Neighbors - Variants of K-Means Algorithm (Clustering Road Transport Data) - Hierarchical clustering - DBSCAN - Self-Organizing Feature Map - Fuzzy C-means (Clustering Microarray Gene Expression Data)

Module 5: Tree and Rule Based Models

Tree Based Models: Decision Trees - Ranking and Probability estimation Trees - Regression trees - Classification and Regression Trees (CART) (Application of CART algorithm using hepatitis disease diagnosis); Rule Based Models: learning ordered rule lists - learning unordered rule lists - descriptive rule learning - association rule mining - first-order rule learning (Application of rule based algorithm using agriculture dataset)

Module 6: Model Performance Evaluation

Cross Validation - Grid Search - Evaluation Metrics and Scoring of Classification, Regression and Clustering Models - Loss Functions and Regularization (Model Evaluation using Air pollution Data)