Knowledge Graph — Coursera Notes › Academic disciplines › Information Technology / Computer Science › Machine Learning › Ensemble methods

Boosting

concept · part of Ensemble methods

Boosting is an ensemble machine learning technique that sequentially trains weak learners, each focusing on correcting the errors of its predecessor, to create a strong predictive model. It matters because it often achieves high accuracy and is widely used in applications like ranking, classification, and regression.

Inside Boosting (2)

• AdaBoost — AdaBoost is a boosting technique that gives misclassified samples higher weights in the next iteration, focusing on difficult cases.
• Gradient Boosting Machines (GBMs) — GBMs use gradient descent to optimize a loss function, making adjustments to the model at each step.

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.