Progress in artificial intelligence

Progress in machine classification of images ---- The error rate of AI by year. Red line - the error rate of a trained human

Artificial intelligence applications have been used in a wide range of fields including medical diagnosis, stock trading, robot control, law, scientific discovery and toys. However, many AI applications are not perceived as AI: "A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore."^[1] "Many thousands of AI applications are deeply embedded in the infrastructure of every industry."^[2] In the late 1990s and early 21st century, AI technology became widely used as elements of larger systems,^[2][3] but the field is rarely credited for these successes.

To allow comparison with human performance, artificial intelligence can be evaluated on constrained and well-defined problems. Such tests have been termed subject matter expert Turing tests. Also, smaller problems provide more achievable goals and there are an ever-increasing number of positive results.

Performance evaluation

The broad classes of outcome for an AI test are:

• optimal: it is not possible to perform better
• strong super-human: performs better than all humans
• super-human: performs better than most humans
• par-human: performs similarly to most humans
• sub-human: performs worse than most humans

Optimal

• Tic-Tac-Toe
• Connect Four
• Checkers^[4]
• Rubik's Cube^[5]
• Heads-up limit hold'em poker: statistically optimal in the sense that "a human lifetime of play is not sufficient to establish with statistical significance that the strategy is not an exact solution".^[6] Sub-human for full ring Texas hold 'em; approaching strong super-human in simpler versions of poker.^[7]

Strong super-human

• Bridge: nearing strong super-human^[8]
• Chess: nearing strong super-human^[9]
• Go: nearing strong super-human; better than European Go champion^[10]
• Jigsaw puzzles: strong super-human^[11]
• Reversi: strong super-human^[12]
• Scrabble: strong super-human^[13]
• Quiz show question answering: strong super-human^[14][15]

Super-human

• Backgammon: super-human^[16]
• Crosswords: super-human^[17]
• Driving a car: super-human. Google driverless cars are safer and smoother when steering themselves than when a human takes the wheel.^[18]
• Arimaa: super-human^[19]

Par-human

• Optical character recognition for ISO 1073-1:1976 and similar special characters.
• Classification of images^[20]

Sub-human

• Optical character recognition for printed text (nearing par-human for Latin-script typewritten text)
• Handwriting recognition
• Object recognition
• Translation^[21]
• Speech recognition
• Word-sense disambiguation
• Natural language processing

See also

• Applications of artificial intelligence
• List of artificial intelligence projects
• List of emerging technologies

External links

• http://www.human-competitive.org/

References

1. AI set to exceed human brain power CNN.com (July 26, 2006)
2. Kurtzweil 2005, p. 264
3. NRC 1999 under "Artificial Intelligence in the 90s"
4. Schaeffer, J.; Burch, N.; Bjornsson, Y.; Kishimoto, A.; Muller, M.; Lake, R.; Lu, P.; Sutphen, S. (2007). "Checkers is solved". Science 317 (5844): 1518–1522. Bibcode:2007Sci...317.1518S. doi:10.1126/science.1144079. PMID 17641166. CiteSeerX: 10.1.1.95.5393.
5. "God's Number is 20".
6. Bowling, M.; Burch, N.; Johanson, M.; Tammelin, O. (2015). "Heads-up limit hold'em poker is solved". Science 347 (6218): 145–9. doi:10.1126/science.1259433. PMID 25574016.
7. Rubin, Jonathan; Watson, Ian (2011). "Computer poker: A review". Artificial Intelligence 175: 958–987. doi:10.1016/j.artint.2010.12.005.
8. Computer bridge#Computers versus humans
9. Computer Chess#Computers versus humans
10. "Mastering the game of Go with deep neural networks and tree search". 2016. (pdf)
11. "Computer software sets new record for solving jigsaw puzzle".
12. Reversi#Computer opponents
13. Sheppard, B. (2002). "World-championship-caliber Scrabble". Artificial Intelligence 134: 241–275. doi:10.1016/S0004-3702(01)00166-7.
14. Watson beats Jeopardy grand-champions. http://www.nytimes.com/2011/02/17/science/17jeopardy-watson.html
15. Jackson, Joab. "IBM Watson Vanquishes Human Jeopardy Foes". PC World. IDG News. Retrieved 2011-02-17.
16. Tesauro, Gerald (March 1995). "Temporal difference learning and TD-Gammon". Communications of the ACM 38 (3): 58–68. doi:10.1145/203330.203343.
17. Proverb: The probabilistic cruciverbalist. By Greg A. Keim, Noam Shazeer, Michael L. Littman, Sushant Agarwal, Catherine M. Cheves, Joseph Fitzgerald, Jason Grosland, Fan Jiang, Shannon Pollard, and Karl Weinmeister. 1999. In Proceedings of the Sixteenth National Conference on Artificial Intelligence, 710-717. Menlo Park, Calif.: AAAI Press.
18. http://www.technologyreview.com/news/520746/data-shows-googles-robot-cars-are-smoother-safer-drivers-than-you-or-i/
19. According to http://arimaa.com/arimaa/challenge/, "The Arimaa Challenge was won on April 18, 2015 and is no longer available."
20. "Microsoft researchers say their newest deep learning system beats humans -- and Google - VentureBeat - Big Data - by Jordan Novet". VentureBeat.
21. There are several ways of evaluating machine translation systems. People competent in a second language frequently outperform machine translation systems but the average person is often less capable. Some machine translation systems are capable of a large number of languages, like google translate, and as a result have a broader competence than most humans. For example, very few humans can translate from Arabic to Polish and French to Swahili and Armenian to Vietnamese. When comparing over several languages machine translation systems will tend to outperform humans.