Glossary of AI terminology

Data mining is the process of analyzing large data sets to identify important patterns. Data mining algorithms use sequence analysis, classification and clustering to establish relationships for analysis within data.

Deep learning is a type of machine learning in which a set of linked algorithms mimic the structure and function of the brain in artificial neural networks. While traditional machine learning algorithms are linear, deep learning algorithms are stacked (hence, “deep”) in a hierarchy of increasing complexity and abstraction. To master this complexity, neural networks require large amounts of data and processing power to “learn.”

Machine learning is the science of getting computers to do what is second nature to people—learning from experience.  Machine learning algorithms are typically designed for specific tasks, such as facial recognition or malware detection. The algorithms are “trained” on large volumes of data. They learn and improve on their own without being explicitly programmed.

Machine vision allows computers to “see” by capturing and analyzing visual information via camera, analog‑to‑digital conversion or digital signal processing. While it is often compared to human eyesight, machine vision is not bound by biology and can process infrared, ultraviolet and X‑ray wavelengths.

Natural language processing (NLP) uses sets of algorithms to allow computers to understand human language as it is spoken or written. Using deep‑learning models, NLP algorithms analyze unstructured data to interpret ambiguous and complex linguistic structures, including social context, slang and regional dialects.

Voice recognition is an underlying technology of NLP that allows machines to analyze human speech and to understand and carry out spoken commands. Voice recognition software converts analog audio into digital signals which it then deciphers using pattern recognition and a digital database vocabulary.