On Wednesday 14 March 2007 20:00, Ben Goertzel wrote: > ... > Then, we can submit a query of the form > > m(specific state, specific input, variable output, variable next state) > = m(S,I,$O,$NS) > > using $ to precede variables
So far, so good. The relation is simply being used to store the table definition of the FSA. > > And this can be resolved via "analogical quadrature", which means that > we look at all > vectors Xi whose first 2m components are similar to (S,I), and average > the final 2m > components of all these vectors to get a guess for ($O, $NS). [Of > course, there are many > ways to do this weighted-averaging.] > > Is this what you're suggesting? I didn't mention AQ. It wouldn't get used if the table actually specified a complete FSA. It WOULD get used if the query specified a combo that wasn't in the table. In this simple case, AQ would amount to interpolating the table, essentially as you said. This is all pretty simple at lower levels -- it basically gives you the ability to program a simple controller by letting it "play" in the space and accumulate enough memories (points) that it predicts the shape of the space adequately. > > The key paradigm shift is to the circuit. Now each of the inputs is a > > time-varying signal and so are the outputs. But now I *can* simply > > connect the output state signal to the input, because there's an implicit > > delay along the wire (or in the predicate). And now, bingo, it's a > > self-running machine. > > I'm not sure I follow your "paradigm shift". > > If the input varies, then for input[t] one can do analogical quadrature > and get output[t+S] and nextState[t+S], > assuming the quadrature process takes S time units. Then one can set > > state[t+S+R] = nextState[t+S] > > Is that what you mean? For simplicity ignore AQ and assume all necessary points are in memory. Then state[t+delay] = nextstate[t] --but this is an equation, not an assignment, and it's valid for all the continuous values of t, not just a sequence of discrete states (although discrete states can be generated by the shape of the surface). > What I don't really get is why you think this "analogical quadrature" > operator is so powerful that it > can serve as the core of a cognitive engine.... The engine is the associative memory; AQ is the interpolater. But it's the representation that makes any scheme live or die, and that remains entirely to be worked out. We'll have to go over this in more detail later. Josh ----- 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/?list_id=303
