Dr. Mark Humphrys

School of Computing. Dublin City University.

Home      Blog      Teaching      Research      Contact

Search:

CA216      CA249      CA318

CA400      CA651      CA668


Open Issues in AI

We have now a spectrum of techniques of search, learning and evolution. How do we put all these together? Some open issues in AI:

  1. Architectures of Mind - What does the whole mind look like? Network, Hierarchy or Society? Does I/O link to many brains or one? Who is in charge? Where am I? What is consciousness?

  2. Action Selection - As a more specific example of the above. We know how to solve 1 problem. How does the creature deal with multiple problems at once?

  3. "Learning to Learn" - How does the creature generate goals for itself in the first place? Machine learning algorithms all learn for a while and then converge (stop learning). Why do humans not converge?

  4. Symbol-grounding, Evolution of language. - What is language? How do creatures processing numerical sensory data end up processing symbolic "words" with meanings? What does "chair" mean, internally? Is it a meaningless token #5099 being passed around, or is it a whole specialised sub-system, firing away? Do parts of the brain talk to each other? Do we have an internal language? Is it English, or is it something more messy? Will sub-symbolic AI plug in neatly to symbolic AI?

  5. Robots or simulation? - Robots are more real, may solve symbol-grounding. But experiments in simulation (the Web?) are more practical. Sims could never have evolved his 3-D robots in hardware. (Though a field of Evolutionary Hardware does exist.)



Feeds      w2mind.org

On Internet since 1987.