I suppose the output could be continuous? meaning that as long as there was some kind of monad like isolation of values you could "sample" the inhibition at whatever rate you wanted without having to "freeze" the state at any particular point?
On Thu, Mar 5, 2015 at 7:30 PM, cogmission <[email protected]> wrote: > Sorry we got out of sync, my question regarding the columns representing > sparse bits by the inhibition of whole topographies stands... For every > input there is a resultant output, so that implies some kind of sync'ing > right? > > On Thu, Mar 5, 2015 at 7:27 PM, Rich Morin <[email protected]> wrote: > >> On Mar 5, 2015, at 17:08, cogmission <[email protected]> wrote: >> > ... all bits could be processed at once or in chunks equal to the >> > number of cores doing the processing (x 2 if you figure in the >> > Hyper-Threading in the case of an Intel CPU) >> >> I'm thinking more in terms of lightweight (Elixir/Erlang) processes as >> the "actors", so there could be one for each neuron, column, or region >> as desired. This could make maintaining sequentiality more difficult. >> >> -r >> >> -- >> http://www.cfcl.com/rdm Rich Morin [email protected] >> http://www.cfcl.com/rdm/resume San Bruno, CA, USA +1 650-873-7841 >> >> Software system design, development, and documentation >> >> >> >> > > > -- > *We find it hard to hear what another is saying because of how loudly "who > one is", speaks...* > -- *We find it hard to hear what another is saying because of how loudly "who one is", speaks...*
