Ben, >From reading the list of publications, it looks just like you said. Most of its individual papers relate to how to make computers gain a particular competency that we hope our systems would learn largely automatically.
But some of the black boxes sound quite interesting. Like one of the papers was entitled "Hierarchical Hidden Markov Models with General State Hierarchy." This is a basic general concept which, with modification, could be quit useful in an AGI as a way for matching (particularly temporal) hierarchical models against perceptual inputs or feedback. Jim Baker, the Guru at Dragon Systems said if he had time he would really like to get into Markov fields which are the n-dimensional extension of Markov Models (which generally are, with the exception of branching, one dimensional). So presumably the concept of hierarchical hidden Markov models could be extended to general pattern matching. Ed -----Original Message----- From: Benjamin Goertzel [mailto:[EMAIL PROTECTED] Sent: Friday, November 30, 2007 1:05 PM To: agi@v2.listbox.com Subject: Re: FW: [agi] AGI DARPA-style Yeah, I've been following that for a while. There are some very smart people involved, and it's quite possible they'll make a useful software tool, but I don't feel they have a really viable unified cognitive architecture. It's the sort of architecture where different components are written in different programming languages based on unrelated ideas and are hooked together in an overall architecture, interacting with each other as black boxes. No emergent intelligence via inter-component interactions is likely to arise in this approach.... And of course the lack of embodiment makes any solution to the symbol-grounding problem unlikely to emerge... -- Ben On Nov 30, 2007 12:59 PM, Ed Porter <[EMAIL PROTECTED]> wrote: > Also checkout http://caloproject.sri.com/publications/ for a list of CALO > related publications > > Ed Porter > > > -----Original Message----- > From: Ed Porter [mailto:[EMAIL PROTECTED] > Sent: Friday, November 30, 2007 12:58 PM > To: 'agi@v2.listbox.com' > Subject: RE: [agi] AGI DARPA-style > > Checkout AGI DARPA-style: > > "Software That Learns from Users-- A massive AI project called CALO could > revolutionize machine learning" at > http://www.technologyreview.com/Infotech/19782/?a=f > > Ed Porter > > ----- > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; > ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=70924924-d38edd
