Introduction to AI & Machine Learning

Explore types of machine learning—supervised, unsupervised, and reinforcement learning—and see how labeled data, unlabeled data, and feedback drive learning in a spam email filter, customer segmentation, and robot training.

Explore supervised learning by comparing regression and classification, distinguishing continuous outputs from discrete categories, with examples like stock price forecasts and object recognition.

Learn how linear regression models a relationship between one or more inputs and a single output, using training data, scatterplots, and fitting lines or hyperplanes to predict house prices.

Explore polynomial regression by transforming inputs into polynomial features (x, x^2, x^3), turning non-linear fitting into a multiple linear regression problem.

Learn logistic regression for binary classification, using the sigmoid function to map input features to a probability and classify as 1 or 0.

Explore artificial neural networks inspired by the human brain, including neurons with inputs, weights, bias, and a sigmoid (logistic) activation that yields the output Y.

Explore how artificial neural networks use weights, biases, and logistic activation to build multi-layer deep learning models that map inputs to outputs through hidden layers.

Explore how unsupervised learning uses clustering to group unlabelled data into clusters, covering centroid-based, density-based, hierarchical-based, and distribution-based methods, including k-means and dbscan for applications like customer segmentation.

Advance your AI and machine learning basics by exploring core algorithms, motivation, and concepts, and explore the course artificial intelligence and machine learning from scratch for deeper study.