Machine Learning Fundamentals and Types
Description
Understanding core machine learning concepts, algorithms, and different learning paradigms including supervised, unsupervised, and reinforcement learning
Learning Objectives
Learners will understand fundamental machine learning concepts including supervised learning (regression and classification), unsupervised learning (clustering), and reinforcement learning. They will be able to identify appropriate machine learning techniques for different scenarios and understand the concepts of training and validation datasets, features, and labels.
Topics (8)
Comprehensive introduction to ML including its relationship to AI and fundamental concepts
Learning about linear regression, polynomial regression, and other regression techniques
Learning about logistic regression, decision trees, support vector machines, and neural networks
Learning about k-means, hierarchical clustering, and other unsupervised techniques
Learning about artificial neurons, multi-layer perceptrons, and deep network architectures
Learning about attention mechanisms, encoder-decoder architecture, and transformer models
Learning about data splitting, cross-validation, and model evaluation methodologies
Learning about data features, feature extraction, dimensionality reduction, and label encoding