Arthur Samuel
In plain wordsAn American IBM engineer whose checkers program improved by playing against itself, and whose 1959 paper helped make 'machine learning' the name of a field.
American computer scientist at IBM (1949–1966) and later Stanford University who wrote one of the first programs that improved with experience: a checkers (draughts) player developed from the early 1950s on IBM's first commercial computers. The program searched a game treegame tree, n.: A branching diagram of every way a game could unfold: each point is a position, each branch a possible move, and the tips of the branches are wins, losses or draws. with minimaxminimax, n.: A way for a game-playing program to choose moves by assuming the opponent will always make their best reply, and picking the move whose worst-case outcome is best. and pruning, memorized positions it had already evaluated (rote learning), and adjusted the weights of its evaluation function by comparing a position's score with the score found by searching deeper later in play — an early form of temporal difference learningtemporal difference learning, n.: A way of learning predictions by adjusting each guess toward the next, slightly better-informed guess instead of waiting for the final outcome — like revising a weather forecast every day as the date approaches. — partly by playing versions of itself (self-playself-play, n.: Training an AI by having it play against copies of itself, so it always has an opponent at its own level and can keep improving without human examples.). His 1959 paper 'Some Studies in Machine Learning Using the Game of Checkers' is the best-known early use of the phrase 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.. In 1962 the program won a widely publicized game against the strong human player Robert Nealey.
Usage note
The often-quoted definition of machine learning as giving computers the ability to learn without being explicitly programmed is a later paraphrase of his views; it does not appear verbatim in his 1959 paper.
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.
- self-playself-play, n.: Training an AI by having it play against copies of itself, so it always has an opponent at its own level and can keep improving without human examples.
- temporal difference learningtemporal difference learning, n.: A way of learning predictions by adjusting each guess toward the next, slightly better-informed guess instead of waiting for the final outcome — like revising a weather forecast every day as the date approaches.
- minimaxminimax, n.: A way for a game-playing program to choose moves by assuming the opponent will always make their best reply, and picking the move whose worst-case outcome is best.
- game treegame tree, n.: A branching diagram of every way a game could unfold: each point is a position, each branch a possible move, and the tips of the branches are wins, losses or draws.
- alpha–beta pruningalpha–beta pruning, n.: A shortcut for game programs: tracking the best result each side is already sure of, it ignores lines of play that could only do worse, and when promising moves come first it searches about twice as deep.
Sources
- Samuel, A. L. (1959). Some Studies in Machine Learning Using the Game of Checkers. IBM Journal of Research and Development 3(3): 210–229.
Mentioned in
Dartmouth workshopDartmouth workshop, prop. n.: A summer meeting of scientists at Dartmouth College in 1956, planned in a 1955 funding proposal that first used the phrase 'artificial intelligence'. Most histories treat it as the moment AI became a research field of its own., evaluation functionevaluation function, n.: In a game-playing program, a formula that looks at a board position and gives it a score saying how good it is, without playing the game out to the end., IBM ResearchIBM Research, prop. n.: The research division of the computer company IBM, behind landmark AI systems such as the chess champion Deep Blue and the quiz-show winner Watson., Samuel's checkers programSamuel's checkers program, prop. n.: A 1950s IBM program by Arthur Samuel that learned to play checkers better than its author, partly by playing against itself. It was among the first programs to learn, and its 1959 paper popularized the phrase 'machine learning'.