[pdp-discuss] LSTM/RBP

[Dmitry Kit]

I'm sorry, but I've never used the wizard. First do you mean the RNS
network? Second after I click OK on the wizard nothing happens. Is something
supposed to happen? I'm not sure what you mean by the context layer...
         Thank you,
               --Dmitry Kit


On 12/5/05, Randall C. O'Reilly <oreilly at psych.colorado.edu> wrote:
>
> This is not an inappropriate usage.  LSTM is difficult to setup correctly,
> but
> RBP should work without too much difficulty -- it does require attention
> to
> the appropriate architecture and parameters.  You might want to just start
> with an SRN (just add a context layer to a feedforward backprop net -- the
> wizard will do this for you) -- it is the most foolproof and will work
> pretty
> well, but not as well as the others.  This will give you a quick
> first-pass
> sense of whether there is any regularity at all.
>
> - Randy
>
> On Monday 05 December 2005 08:46 pm, Dmitry Kit wrote:
> > Hello everyone,
> >
> > I have the following problem. I have resource usage trace of a program
> and
> > want to see if I can predict the next usage level. The numbers are all
> > between 0 and 1. I was thinking a recurrent neural net would be ideal
> for
> > this situation. Given a current usage pattern give the next pattern as
> the
> > output target. What I see however is the net quickly reaching a steady
> > state where some units are always on and others are always off.
> >
> > The question is this even a good use of recurrent nets? I know it works
> > with n inputs activated in a certain pattern (0 or 1). In my case I only
> > have one input and the activation is fairly close together, although I
> > don't see why the output settles on a high activation value (1). I don't
> > want to spend too much time on this if I'm using it incorrectly.
> >
> >          Best Regards,
> >                        Dmitry
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://psych-srv3.Colorado.EDU/pipermail/pdp-discuss/attachments/20051206/90180e6d/attachment.html