" I believe that in about fifty years time it will be possible to programme computers, with a storage capacity of about 10 to the power 9, to make them play the imitation game so well that an average interrogator will not have more than 70 percent chance of making the right identification after 5 minutes of questioning"
Alan Turing (1950)
Turing Test
"Turing was convinced that if a computer could do all mathematical operations, it could also do anything a person can do"
Computing Machinery and Intelligence, written by Alan Turing and published in 1950 in Mind, is a paper on the topic of artificial intelligence in which the concept of what is now known as the Turing test was introduced to a wide audience.
Today the Game is usually referred to as the Turing Test.
If a computer can play the game just as well as a human, then the computer is said to 'pass' the 'test', and shall be declared intelligent.
How can we evaluate intelligence?
- Turing [1950]: a machine can be deemed intelligent when its responses to interrogation by a human are indistinguishable from those of a human being.
Total Turing Test
Includes a video signal so that the interrogator can test the subject's perceptual abilities, as well as the opportunity for the interrogator to pass physical objects "through the hatch."
To pass the total Turing Test, the computer will need
- computer vision to perceive objects, and
- robotics to move them about.
How effective is this test?
Agent must:
- Have command of language
- Have wide range of knowledge
- Demonstrate human behavior (humor, emotion)
- Be able to reason
- Be able to learn
Loebner prize competition is modern version of Turing Test
- (The Loebner Prize is an annual competition in artificial intelligence that awards prizes to the chatterbot considered by the judges to be the most human-like.)
- Example: Alice, Loebner prize winner for 2000 and 2001.
Turing Test: Criticism
What are some potential problems with the Turing Test?
- Some human behavior is not intelligent
the temptation to lie, a high frequency of typing mistakes
- Some intelligent behavior may not be human
If it were to solve a computational problem that is practically impossible for a human to solve
- Human observers may be easy to fool
A lot depends on expectations
Chatbots, e.g., ELIZA, ALICE
- Chinese room argument
Is passing the Turing test a good scientific/ engineering goal?
Alan Turing (1950)
Turing Test
"Turing was convinced that if a computer could do all mathematical operations, it could also do anything a person can do"
Computing Machinery and Intelligence, written by Alan Turing and published in 1950 in Mind, is a paper on the topic of artificial intelligence in which the concept of what is now known as the Turing test was introduced to a wide audience.
Today the Game is usually referred to as the Turing Test.
If a computer can play the game just as well as a human, then the computer is said to 'pass' the 'test', and shall be declared intelligent.
How can we evaluate intelligence?
- Turing [1950]: a machine can be deemed intelligent when its responses to interrogation by a human are indistinguishable from those of a human being.
Total Turing Test
Includes a video signal so that the interrogator can test the subject's perceptual abilities, as well as the opportunity for the interrogator to pass physical objects "through the hatch."
To pass the total Turing Test, the computer will need
- computer vision to perceive objects, and
- robotics to move them about.
How effective is this test?
Agent must:
- Have command of language
- Have wide range of knowledge
- Demonstrate human behavior (humor, emotion)
- Be able to reason
- Be able to learn
Loebner prize competition is modern version of Turing Test
- (The Loebner Prize is an annual competition in artificial intelligence that awards prizes to the chatterbot considered by the judges to be the most human-like.)
- Example: Alice, Loebner prize winner for 2000 and 2001.
Turing Test: Criticism
What are some potential problems with the Turing Test?
- Some human behavior is not intelligent
the temptation to lie, a high frequency of typing mistakes
- Some intelligent behavior may not be human
If it were to solve a computational problem that is practically impossible for a human to solve
- Human observers may be easy to fool
A lot depends on expectations
Chatbots, e.g., ELIZA, ALICE
- Chinese room argument
Is passing the Turing test a good scientific/ engineering goal?
No comments:
Post a Comment