Arthur Samuel

Infobox_Scientist
name = Arthur Samuel


image_width =
caption =
birth_date = 1901
birth_place = Emporia, Kansas
death_date = July 29, 1990
death_place = Stanford, CA
residence =
citizenship = United States
nationality = American
ethnicity =
field = Computer Science
work_institution =
alma_mater = MIT
doctoral_advisor =
doctoral_students =
known_for = Samuel Checkers-playing Program
author_abbreviation_bot =
author_abbreviation_zoo =
prizes =
religion =
footnotes =

Arthur L. Samuel (1901 – July 29, 1990) was a pioneer in the field of computer gaming and artificial intelligence. The Samuel Checkers-playing Program appears to be the world's first self-learning program, and as such a very early demonstration of the fundamental concept of artificial intelligence (AI). [cite news | first= | last= | coauthors= | title=MEMORIAL RESOLUTION | date= | publisher= | url =http://www.google.com/search?q=cache:fBmy-cdHMDkJ:histsoc.stanford.edu/pdfmem/SamuelA.pdf+Arthur+Samuel+emporia&hl=en&ct=clnk&cd=1&gl=us&client=firefox-a | work = | pages = | accessdate = 2007-04-26 | language = ]

Biography

Samuel attended College of Emporia in Kansas for his undergraduate work, and received a Master’s degree in Electrical Engineering from M.I.T. In 1928, he joined Bell Laboratories, where he labored mostly on hardware; what we would today call Computer Engineering, but before computers. After a stint at UIUC, Samuel went to IBM, where he would conceive and carry out his most successful work. It was at IBM that he made the first checkers program on IBM's first commercial computer, the IBM 701. The program was a sensational demonstration of the advances in both hardware and skilled programming and caused IBM's stock to increase 15 points overnight. His pioneering non-numerical programming helped shaped the instruction set of processors, as he was one of the first to work with computers on projects other than computation. In 1966, Samuel became a professor at Stanford, where he worked the remainder of his life. He died of complications from Parkinson's disease in 1990.

Computer checkers (draughts) development

Samuel is most known within the AI community for his groundbreaking work in computer checkers. He thought that teaching computers to play games was very fruitful for developing tactics appropriate to general problems, and he chose checkers because it is relatively simple, but has a depth of strategy. The main driver of the machine was a search tree of the board positions reachable from the current state. Since he had only a very limited amount of memory, Samuel implemented what is now called alpha-beta pruning. Instead of searching each path until it came to the game’s conclusion, Samuel developed a scoring function based on the position of the board at any given time. This function tried to measure the chance of winning for each side at the given position. It took into account such things as the number of pieces on each side, the number of kings, and the proximity of pieces to being “kinged”. The program chose its move based on a minimax strategy, meaning it made the move that optimized the value of this function, assuming that the opponent was trying to optimize the value of the same function from its point of view. [ cite journal|title=Some Studies in Machine Learning Using the Game of Checkers|journal=IBM Journal|date=1959-03-03|first=Samuel|last=Arthur|coauthors=|volume=3|issue=3|pages=210–229|id= |url=http://www.research.ibm.com/journal/rd/033/ibmrd0303B.pdf|format=PDF|accessdate=2007-04-26]

Samuel also designed various mechanisms by which his program could become better. In what he called rote learning, the program remembered every position it had already seen, along with the terminal value of the reward function. This technique effectively extended the search depth at each of these positions. Samuel's later programs reevaluated the reward function based on inputted professional games. He also had it play thousands of games against itself as another way of learning. With all of this work, Samuel’s program reached a respectable amateur status, and was the first to play any board game at this high of level. He continued to work on checkers until the mid-‘70s, at which point his program became easily beaten by the best of the time. However, his method of learning through games continued, both in continued work on checkers (which was completely solved in 2007 by a computer which explored all relevant positions) and in other games like chess and go.

External links

* [http://infolab.stanford.edu/pub/voy/museum/samuel.html Stanford Obituary]
* [http://www.cs.ualberta.ca/~sutton/book/11/node3.html Biography]
* [http://www.cs.ualberta.ca/~chinook/ Chinook Information]

References