Progress in artificial intelligence

From Wikipedia, the free encyclopedia

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

Contents 1 Performance evaluation 2 Optimal 3 Super-human 4 Sub-human 5 See also 6 References

[edit] 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
• sub-human: performs worse than most humans

[edit] Optimal

• Checkers^[1]

[edit] Super-human

• Backgammon: strong super-human^[2]
• Bridge: nearing strong super-human^[3]
• Chess: nearing strong super-human^[4]
• Reversi: strong super-human^[5]
• Scrabble: strong super-human^[6]

[edit] Sub-human

• Go^[7]
• Machine translation
• Most everyday tasks performed by humans.

[edit] See also

• Technology development

[edit] References

1. ^ Schaeffer, Jonathan (2007-07-19). Checkers Is Solved. Science. Retrieved on 2007-07-20.
2. ^ Tesauro, Gerald (March 1995). "Temporal difference learning and TD-Gammon". Communications of the ACM 38 (3): 58–68. doi:10.1145/203330.203343. 
3. ^ Computer bridge#Computers versus humans
4. ^ Computer Chess#Computers versus humans
5. ^ Reversi#Computer_opponents
6. ^ doi:10.1016/S0004-3702(01)00166-7
7. ^ Computer Go#Computers versus humans