How does 20q radica work

It was right. So how does this 20Q device work? The short answer is "artificial intelligence. In , Canadian inventor Robin Burgener programmed a neural network a specialized form of computer program capable of playing 20 Questions, but without a library of knowledge about common objects.

He proceeded to teach it twenty questions about the object "cat," then handed the program on floppy disk to friends and encouraged them to play, recording their play sessions as it went. For 20Q, playing equals learning, as it develops "synaptic connections" whenever it receives answers to questions. It's able to reinforce connections by playing games over and over with different people, gradually learning which answers are correct and which aren't.

Thus it's difficult to "poison" the system by purposely giving it wrong answers. You can always use the in-App purchase, and you will not be charged if you have already made that purchase. For more information check out A Quick Tour. From the 20Q home page , select Play from the menu on the left, and then select "Play 20Q" choosing one of the languages.

On the next page, answer a few demographic questions and click "Play. Next, think of an object and answer the questions asked by the 20Q Artificial Intelligence A. Click on the answer that fits the object you are thinking of; the questions that follow will be displayed by 20Q with several choices.

Click on what you believe to be the appropriate answer for that question. Don't worry about making a mistake; you can always scroll down and click on the questions to change your answer later. You may change your answer to a question while playing the game.

Select the question from the list of answered questions, then change your answer. You may also use the back button of your web browser, but 20Q may pick different questions than it did the first time. Once the Update button has been pressed, the knowledgebase is permanently modified by the answers you gave it and you won't be able to go back.

Don't despair. Every game changes the knowledgebase a little bit; the game will be corrected over time by you or by other people playing the game. Sometimes when you get to the end of a game 20Q will tell you that there were contradictions. You may notice that 20Q can be wrong. This happens because it tries to reflect human knowledge, not necessarily what is fact.

The one way to correct such "errors" is to play the game thinking about the same object again and again and again. We always like to hear about typos and other strange problems.

Please fill out our contact form and let us know if you find any such problems. When 20Q makes note of some contradictions at the end of the game, it is merely giving you a peek into its state of mind with regard to the object you played.

Since 20Q learns everything it knows from the people who play, it is dealing with opinions, not facts. It's more like a folk taxonomy. Folk taxonomies are generated from social knowledge and are used in everyday speech. As noted in Wikipedia: "They are distinguished from scientific taxonomies that claim to be disembedded from social relations and thus objective and universal. Since the opinions of people often differ, 20Q must do its best to sort out conflicting information.

Contradictions are also one of the main ways that 20Q learns more about something. Because 20Q is continuously learning from so many different teachers , visitors play the game every day , its knowledge is based on an average of the opinions of all of them. This sometimes leads to unexpected results. Every once in a while 20Q hits you with a question that seems completely off the wall.

It then chooses a question that will cut the number of likely objects in half. Because 20Q does not simply follow a binary decision tree, answering a question incorrectly will not throw it completely off. In any situation when someone could misunderstand a question or inadvertently answer incorrectly, the 20Q AI could approximate a human trained in recognizing those types of errors. Like a triage nurse, 20Q could theoretically learn how to accurately diagnose ailments by asking the right questions.

Though applications like these are years away, Burgener is confident that the 20Q AI will eventually be useful in many different ways. Once a helioseismology researcher, once a professional singer, once a neuroscience lab tech, and always a cheesehead.

Hi Karen! Great to know how this 20Q works! So many times having worked for doctors many years one has a hard timegetting peope to explain exactly what ails them in a concise wasy, especially either very young patients or very old patients.

This would really be a great assistant in that process, particularly now that there is often a long wait for treatment ad a form-filling-out process that often does NOT ask the correct or more specific questions! Love, Aunt Luz. I was very curious about how such a large database and the program to access it could have been placed on a relatively small chip.

A good timepass for everyone. I guessed panties, porcupine, beef, zebra and it guessed right. How does it do so? It was packaged at the store so you could test it out and it instantly blew my mind. I recently moved and found it in a drawer I was cleaning out. The answer to my question was an iPhone. It guessed PDA, like a palm pilot which considering how much time has passed since I bought it and the iPhone was just about to be introduced into the market or was just released, I was amazed at how close it s guess was.