pattern recognition
In plain wordsThe ability of a computer, or a brain, to spot regularities in data and sort things into categories, such as recognizing handwritten letters, faces or spoken words.
- 1
Field
The branch of engineering and computer science that builds systems to sort inputs, such as images, signals, speech or text, into categories or to describe their structure, using models learned from examples or supplied by designers. Classical systems split the problem into preprocessing, feature extractionfeature extraction, n.: Turning raw data such as pixels or sound into a short list of telling numbers — computed by hand-designed rules or by an AI system trained earlier — that a new model can learn from or compare. and classification, drawing on statistical methods (Bayesian decision theory, discriminant analysis, nearest neighbors), structural approaches based on grammars, and neural networksneural network, n.: A kind of computer program that learns a task from examples by tuning thousands to billions of connections between simple number-crunching units, an arrangement loosely inspired by nerve cells in the brain.. Applications included optical character recognitionoptical character recognition, n.: Software that picks out the letters and words in a picture — a road sign, a handwritten note, a page of an old book — and turns them into real text a computer can copy, search or read aloud., speech recognitionspeech recognition, n.: Technology that turns spoken words into written text, as when a phone transcribes a voice message or captions appear automatically under a video., fingerprint and face identification and medical signal analysis. The field is now largely continuous with machine learningmachine learning, n.: A way of building software that learns from examples instead of following rules written by a programmer. Shown thousands of labeled photos, for instance, a program can learn to recognize cats., a merger reflected in the title of Christopher Bishop's textbook Pattern Recognition and Machine Learning (2006).
Cheque-reading machines were among the first commercial successes of pattern recognition.
- 2
Cognition
The cognitive ability to identify objects, faces, sounds or situations by matching sensory input against learned structure. Debates about large language models often ask whether their abilities amount to sophisticated pattern recognition or to genuine reasoningreasoning, n.: Working out conclusions step by step from facts, rules or evidence, as in solving a math problem or planning a trip. Whether today's AI truly reasons, or imitates reasoning, is debated..
Origin
Emerged in the 1950s with early character readers and Oliver Selfridge's 1955 paper 'Pattern Recognition and Modern Computers'. Institutions followed: the journal Pattern Recognition (1968), the International Association for Pattern Recognition (1978) and the IEEE Transactions on Pattern Analysis and Machine Intelligence (1979). Richard Duda and Peter Hart's Pattern Classification and Scene Analysis (1973) became a standard text.
Usage note
Calling an AI system 'just pattern recognition' is usually meant dismissively, but the phrase names a broad and rigorous field, and whether reasoning reduces to pattern recognition is itself contested.
Related
- machine learningmachine learning, n.: A way of building software that learns from examples instead of following rules written by a programmer. Shown thousands of labeled photos, for instance, a program can learn to recognize cats.
- classificationclassification, n.: Sorting things into categories — spam or not spam, which animal is in a photo, which language a text is written in — by learning from examples that are already labeled.
- feature extractionfeature extraction, n.: Turning raw data such as pixels or sound into a short list of telling numbers — computed by hand-designed rules or by an AI system trained earlier — that a new model can learn from or compare.
- computer visioncomputer vision, n.: The part of AI that lets computers make sense of images and video: recognizing faces, reading signs, spotting tumors on scans or judging how far away a car is.
- optical character recognitionoptical character recognition, n.: Software that picks out the letters and words in a picture — a road sign, a handwritten note, a page of an old book — and turns them into real text a computer can copy, search or read aloud.
- speech recognitionspeech recognition, n.: Technology that turns spoken words into written text, as when a phone transcribes a voice message or captions appear automatically under a video.
- neural networkneural network, n.: A kind of computer program that learns a task from examples by tuning thousands to billions of connections between simple number-crunching units, an arrangement loosely inspired by nerve cells in the brain.
- reasoningreasoning, n.: Working out conclusions step by step from facts, rules or evidence, as in solving a math problem or planning a trip. Whether today's AI truly reasons, or imitates reasoning, is debated.
Sources
- Selfridge, O. G. (1955). Pattern Recognition and Modern Computers. Proceedings of the Western Joint Computer Conference.
- Duda, R. O. & Hart, P. E. (1973). Pattern Classification and Scene Analysis. Wiley.
- Bishop, C. M. (2006). Pattern Recognition and Machine Learning. Springer.
Mentioned in
computer visioncomputer vision, n.: The part of AI that lets computers make sense of images and video: recognizing faces, reading signs, spotting tumors on scans or judging how far away a car is., image classificationimage classification, n.: Teaching a computer to say what a picture shows by choosing a label, such as 'cat', 'pneumonia' or 'stop sign', from a fixed list of possibilities., optical character recognitionoptical character recognition, n.: Software that picks out the letters and words in a picture — a road sign, a handwritten note, a page of an old book — and turns them into real text a computer can copy, search or read aloud., feature extractionfeature extraction, n.: Turning raw data such as pixels or sound into a short list of telling numbers — computed by hand-designed rules or by an AI system trained earlier — that a new model can learn from or compare., reasoningreasoning, n.: Working out conclusions step by step from facts, rules or evidence, as in solving a math problem or planning a trip. Whether today's AI truly reasons, or imitates reasoning, is debated., Oliver SelfridgeOliver Selfridge, prop. n.: A British-born American computer scientist who pioneered teaching machines to recognize patterns; his 1959 'Pandemonium' model did it through layers of simple, competing detectors.