Re: FW: [agi] WHAT PORTION OF CORTICAL PROCESSES ARE BOUND BY THE BINDING PROBLEM?

2008-07-17 Thread Brad Paulsen
Mike, If memory serves, this thread started out as a discussion about binding in an AGI context. At some point, the terms forward-chaining and backward-chaining were brought up and, then, got used in a weird way (I thought) as the discussion turned to temporal dependencies and hierarchical

Re: Location of goal/purpose was Re: [agi] WHAT SORT OF HARDWARE $33K AND $850K BUYS TODAY FOR USE IN AGI

2008-07-17 Thread Terren Suydam
Will, --- On Tue, 7/15/08, William Pearson [EMAIL PROTECTED] wrote: And I would also say of evolved systems. My fingers purpose could equally well be said to be for picking ticks out of the hair of my kin or for touch typing. E.g. why do I keep my fingernails short, so that they do not

RE: [agi] Patterns and Automata

2008-07-17 Thread John G. Rose
From: Abram Demski [mailto:[EMAIL PROTECTED] John, What kind of automata? Finite-state automata? Pushdown? Turing machines? Does CA mean cellular automata? --Abram Hi Abram, FSM, semiatomata, groups w/o actions, semigroups with action in the observer, etc... CA is for cellular automata.

Re: [agi] Patterns and Automata

2008-07-17 Thread Abram Demski
No, not especially familiar, but it sounds interesting. Personally I am interested in learning formal grammars to describe data, and there are well-established equivalences between grammars and automata, so the approaches are somewhat compatible. According to wikipedia, semiautomata have no