Definition: machine learning

A major component of artificial intelligence (AI). Machine learning software, which is mostly implemented using a "neural network" architecture, keeps modifying its own algorithms in the training stages in order to become more intelligent and improve future results. Machine learning (ML) is used to enhance pattern recognition (face, handwriting, voice, etc.) in many areas, including search engines, medical diagnosis, ad serving, spam filtering and sales forecasting. Deep learning is a more elaborate form of machine learning, which uses more layers of recognition to discern a pattern. See neural network and deep learning.

Unlike the static logic (if this - do that) in regular programs, machine learning continues to refine its logic over time and with enough samples so that the next operation is more effective than the last. Today's virtual assistants are often a combination of machine learning and "handcrafting," the latter providing predefined frameworks for responses. See AI and computer vision.

The Hierarchy

Machine learning (ML) is a subset of AI, and deep learning is a more elaborate form of ML.