April 26, 2007 at 16:3120Q.net self-learning neural network has already asked a billion questions
Experimental artificial intelligence 20Q.net overcame the mark of 50 million tests and came close to the mark of a billion questions. This neural network is based on the game “Twenty Questions”. A person guesses a word, and his system guesses, taking into account his age, gender and nationality in the process of communication with a person.
Artificial intelligence trains on people. Receiving answers from us, he replenishes his knowledge base. A billion answers means that now he is able to guess almost any human thought.
To check, guess the word "UFO"and see how quickly the system can guess it. As answers, you can choose not only “yes” and “no”, but also fuzzy categories: maybe, perhaps, it is doubtful, partially, etc., and also mark questions as irrelevant.
Question 1. Is it an animal, plant or mineral? Other
Question 2. Do you keep it during use? An irrelevant question.
Question 3. Is it in the office? Not.
Question 4. Do you use it at night? An irrelevant question.
Question 4-2. Is it useful? Unknown
Question 5. Is it more than a microwave? Yes.
Question 6. Is it cold-blooded? An irrelevant question.
Question 7. Can I buy it? Not.
Question 8. Can I put something there? Probably.
Question 9. Does it have a hard shell? Yes.
Question 10. Is it metallic? Yes.
Question 11. Does it provide protection? Yes.
Question 12. Is it direct? Not.
Question 13. Can I live in it? Yes.
Question 14. Is it glowing? Sometimes.
Question 15. Can it be very hot? Probably.
Question 16. Can it be refilled? An irrelevant question.
Question 17. Is this a spaceship ? Close.
Question 18. Have you seen this in life? Not.
Question 19. Will it break if it falls? Not.
Question 20. Is it a space station ? Close.
Question 21. Can you control it? Not.
Question 22. Does it come in different colors? May be.
Question 23. Is it round? Yes.
Question 24. Can I hear it? Yes.
Is it a UFO?
Very good. Especially considering that the 17th question was essentially correct. Artificial intelligence is clearly progressing. What if he soon begins to guess words from the first question?
Artificial intelligence trains on people. Receiving answers from us, he replenishes his knowledge base. A billion answers means that now he is able to guess almost any human thought.
To check, guess the word "UFO"and see how quickly the system can guess it. As answers, you can choose not only “yes” and “no”, but also fuzzy categories: maybe, perhaps, it is doubtful, partially, etc., and also mark questions as irrelevant.
Question 1. Is it an animal, plant or mineral? Other
Question 2. Do you keep it during use? An irrelevant question.
Question 3. Is it in the office? Not.
Question 4. Do you use it at night? An irrelevant question.
Question 4-2. Is it useful? Unknown
Question 5. Is it more than a microwave? Yes.
Question 6. Is it cold-blooded? An irrelevant question.
Question 7. Can I buy it? Not.
Question 8. Can I put something there? Probably.
Question 9. Does it have a hard shell? Yes.
Question 10. Is it metallic? Yes.
Question 11. Does it provide protection? Yes.
Question 12. Is it direct? Not.
Question 13. Can I live in it? Yes.
Question 14. Is it glowing? Sometimes.
Question 15. Can it be very hot? Probably.
Question 16. Can it be refilled? An irrelevant question.
Question 17. Is this a spaceship ? Close.
Question 18. Have you seen this in life? Not.
Question 19. Will it break if it falls? Not.
Question 20. Is it a space station ? Close.
Question 21. Can you control it? Not.
Question 22. Does it come in different colors? May be.
Question 23. Is it round? Yes.
Question 24. Can I hear it? Yes.
Is it a UFO?
Very good. Especially considering that the 17th question was essentially correct. Artificial intelligence is clearly progressing. What if he soon begins to guess words from the first question?