Syllabus
Introduction to machine learning and machine learning applications. Data featurization, vectorization, linear algebra, and matrix representations. Supervised learning – linear regression, polynomial regression, logistic regression, Decision Trees, Support Vector Machine and ANN. Regularization, tuning, overfitting, underfitting. Unsupervised learning: Clustering, dimensionality reduction (PCA). Deep Neural networks: multilayer perceptron, transfer learning, edge models. ML model evaluation metrics. Generative AI – LLMs. MLOps – introduction to converting ML models from test bench to production (saving, loading, using trained models).