Introduces linear models for regression and classification, logistic regression, predictive model evaluation, Naive Bayes, tree-based methods, ensembles, support vector machines, and the kernel trick.

Covers artificial neurons, perceptrons, multilayer perceptrons, activation and cost functions, backpropagation, and applications in regression and classification, along with modern deep learning foundations and architectures for text and image.

Discusses ensemble tasks in machine learning, major types of ensemble methods, applications to classification, and hyperparameter tuning strategies for performance optimization.

Introduces natural language processing, including text preprocessing, semantic and vector representations, sentiment analysis, and notions of sequential models, transformers, and large language models.