Autonomous discovery of abstract concepts by a robot

author: Ivan Bratko, Faculty of Computer and Information Science, University of Ljubljana
published: May 3, 2011,   recorded: April 2011,   views: 3391


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

See Also:

Download slides icon Download slides: icannga2011_bratko_adac_01.pdf (500.2┬áKB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 George Spilkov, May 25, 2011 at 9:17 p.m.:

The system learns in a very small and controlled environment (the world of cubes).

How would the system (the program) behave in a real environment. For example: Let's say we attach the program to the control system of a chemical plant of some kind. Let's also say it has access to maintenance information as well. Given the above how much processing power would be needed so the system could learn to run the plant by itself and to know what to do in what situation? How long it has to observe and analyse what happens before it would be able to make the correct maintenance and control decisions by itself?
I have some issues with the approach in this lecture but my main concerns are related to scalability and combinatorial explosion. Would be nice if they were also addressed.

Write your own review or comment:

make sure you have javascript enabled or clear this field: