Key ways in which machine and deep learning are transforming the analysis and simulation of data in particle physics are introduced. Cutting-edge examples based on boosted decision trees and various types of neural networks, and the challenges in their applications, are highlighted. After describing these novel analysis techniques, the talk will touch on the interactions between physics and machine learning as a two-way street enriching both disciplines and helping to meet the present and future challenges of data-intensive science at the high energy and intensity frontiers.