
  ttrraaiinn -- 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 aa ssppeecciiffiieedd aallggoorriitthhmm

  UUSSAAGGEE

        train [<num-updates>] [-report <report-interval> |
            -algorithm <algorithm> | -setOnly]

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

  This will train the network on the current training set. Examples are
  selected based on the training set's example mode. The number of examples
  per weight update is determined by the network's batchSize parameter. A
  batchSize of 0 indicates that the batch size should be the number of
  examples in the training set.

  If the num-updates is given, the network's numUpdates parameter will be
  set. This is the maximum number of weight updates, or batches, allowed
  during training. If not set, the network's previous value will be used.

  The report-interval will set the network's reportInterval parameter, which
  is the number of weight updates between printing training reports. A report
  is always generated after the first and last updates.

  Finally, an algorithm name may be specified. The available algorithms are
  steepest, momentum, dougsMomentum, and deltaBarDelta. deltaBarDelta is only
  available with the "advanced" version of Lens, alens. If not given, the
  previous algorithm is reused. dougsMomentum is the initial default.

  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.

  Training will stop if the total network error on a batch is less than or
  equal to the network's criterion parameter. Training will also stop if the
  unit criterion is achieved. For this to occur, the distance between each
  output unit's activation and its target must be smaller than a certain
  value at the end of every event in every example in the batch. The unit
  criterion for an output unit is given by its group's unitCriterion
  parameter.

  If the net's output file is open, the output units' activations and targets
  will be recorded on each tick.

  _r_e_s_e_t_N_e_t will randomize the weights, clear the momentum direction
  information, and otherwise get the network ready to start training from
  scratch.

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

  To train with delta-bar-delta for 1000 batches, printing a report every 100
  updates:

        lens> train 1000 -r 100 -a deltaBarDelta

  To do it again, just do:

        lens> train

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

  _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, _u_p_d_a_t_e_W_e_i_g_h_t_s, _t_e_s_t, _r_e_s_e_t_N_e_t,
  _u_s_e_T_r_a_i_n_i_n_g_S_e_t, _e_x_a_m_p_l_e_S_e_t_M_o_d_e, _o_p_e_n_N_e_t_O_u_t_p_u_t_F_i_l_e

  ---------------------------------------------------------------------------
    Last modified: Fri Nov 17 12:35:20 EST 2000

