Assume that there are a set of "black boxes", containing things like neural networks or sensors. I'm wondering what the general architecture for a thinking machine might be.

So, for example, black boxes $A \dots Z$ might be:

A: Evaluates a state.

B: Makes suggestions for actions given input.

C: Simulates the result of a next action.

D: Performs/learns recognition on input.

The question is: how do all these fit together?

  • $\begingroup$ I think you should reword because this opens up a can of worms in regard to what constitutes "thinking". Better to use a less controversial term... $\endgroup$ – DukeZhou Aug 2 '19 at 20:17
  • 1
    $\begingroup$ A real life algorithm which comes close to the idea is an enhanced version of the STRIPS problem solver. Instead of the original one, the system is able to learn new rules by observation (rule induction). In theory, such a software is able to improve itself during runtime. $\endgroup$ – Manuel Rodriguez Aug 2 '19 at 20:35
  • $\begingroup$ In order to answer your question precisely, you need to give the definition of a thinking machine. Also, what do you mean by "general architecture"? $\endgroup$ – nbro Aug 2 '19 at 23:39

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.