
  ddeellttaaBBaarrDDeellttaa -- 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 ddeellttaa--bbaarr--ddeellttaa

  UUSSAAGGEE

        deltaBarDelta [<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 delta-bar-delta. The
  arguments are similar to those for _t_r_a_i_n. The momentum term is taken from
  the network's momentum parameter. Other parameters of importance are the
  network's rateIncrement and rateDecrement.

  In this algorithm, each link stores its own learning rate in its lastValue
  field. This is multiplied by the default learning rate (which is taken from
  the first one of the block's, group's, or network's learningRate fields
  that is not NaN). If the link weight takes consecutive steps in the same
  direction, the link's rate is incremented by rateIncrement. If the weight
  step changes direction, the rate is multiplied by rateDecrement to scale it
  back. Thus, rateDecrement is not, strictly speaking, a decrement.

  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> deltaBarDelta 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_o_u_g_s_M_o_m_e_n_t_u_m

  ---------------------------------------------------------------------------
    Last modified: Fri Nov 17 12:37:33 EST 2000

