
  ddoouuggssMMoommeennttuumm -- ttrraaiinnss tthhee nneettwwoorrkk uussiinngg bboouunnddeedd mmoommeennttuumm ddeesscceenntt

  UUSSAAGGEE

        dougsMomentum [<num-updates>] [-report <report-interval> | -setOnly]

  DDEESSCCRRIIPPTTIIOONN

  This is a shortcut for training the network using "Doug's momentum
  descent". The arguments are similar to those for _t_r_a_i_n. The momentum term
  is taken from the network's momentum parameter.

  Doug's momentum descent is similar to standard momentum descent with the
  exception that the pre-momentum weight step vector is bounded so that its
  length cannot exceed 1.0. After the momentum is added, the length of the
  resulting weight change vector can grow as high as 1 / (1 - momentum). This
  change allows stable behavior with much higher initial learning rates,
  resulting in less need to adjust the learning rate as training progresses.

  If the -setOnly flag is used, no training will occur. However, the
  network's numUpdates, reportInterval, and default algorithm will be set.
  This can be used to set the default training behavior in an initialization
  script prior to actually training.

  EEXXAAMMPPLLEESS

  To train for 1000 epochs, printing reports every 100:

        lens> dougsMomentum 1000 -r 100

  SSEEEE AALLSSOO

  _t_r_a_i_n, _s_t_e_e_p_e_s_t, _m_o_m_e_n_t_u_m, _d_e_l_t_a_B_a_r_D_e_l_t_a

  ---------------------------------------------------------------------------
    Last modified: Fri Nov 17 12:37:06 EST 2000

