Menu

setting up global learning rate for AffineComponent

Help
Yan Yin
2015-07-15
2015-07-15
  • Yan Yin

    Yan Yin - 2015-07-15

    Hi All,

    I want to setup using global learning rate instead of learning rate matrix, I am doing below, it seems I got model with all NaN values for network weights. I guess I must have done something wrong. So anyone please tell me what goes wrong with it?

    AffineComponent input-dim=xxx output-dim=xxx learning-rate=xxx param-stddev=xxx bias-stddev=xxx

    thanks,
    Yan

     
    • Daniel Povey

      Daniel Povey - 2015-07-15

      What you are encountering is instability; it is a common problem in
      neural network training.
      The "preconditioned" version of the component has two things that
      prevent instability: it has the natural-gradient update, and it has
      the "max-change" parameter which limits the parameter change per
      minibatch.
      If you want to do without those, you could try just decreasing the
      learning rate until it's stable.
      Dan

      On Wed, Jul 15, 2015 at 11:16 AM, Yan Yin riyijiye1976@users.sf.net wrote:

      Hi All,

      I want to setup using global learning rate instead of learning rate matrix,
      I am doing below, it seems I got model with all NaN values for network
      weights. I guess I must have done something wrong. So anyone please tell me
      what goes wrong with it?

      AffineComponent input-dim=xxx output-dim=xxx learning-rate=xxx
      param-stddev=xxx bias-stddev=xxx

      thanks,
      Yan


      setting up global learning rate for AffineComponent


      Sent from sourceforge.net because you indicated interest in
      https://sourceforge.net/p/kaldi/discussion/1355348/

      To unsubscribe from further messages, please visit
      https://sourceforge.net/auth/subscriptions/

       
MongoDB Logo MongoDB