Lines Matching full:weights
516 * outputs = activation(inputs * weights? + bias)
530 * weights, and "batch_size" is calculated by dividing the number of
532 * * 1: A 2-D tensor, specifying the weights, of shape
841 * * The input-to-input weights (\f$W_{xi}\f$), recurrent-to-input weights
842 * (\f$W_{hi}\f$), cell-to-input (\f$W_{ci}\f$) weights, and input gate
850 * * The cell-to-forget weights (\f$W_{cf}\f$) and cell-to-output weights
853 * if CIFG is not used, cell-to-input weights (\f$W_{ci}\f$) is also
855 * * The projection weights (\f$W_{proj}\f$) is required only for the
888 * * 1: The input-to-input weights (\f$W_{xi}\f$). Optional.
892 * * 2: The input-to-forget weights (\f$W_{xf}\f$).
895 * * 3: The input-to-cell weights (\f$W_{xc}\f$).
898 * * 4: The input-to-output weights (\f$W_{xo}\f$).
901 * * 5: The recurrent-to-input weights (\f$W_{hi}\f$). Optional.
906 * * 6: The recurrent-to-forget weights (\f$W_{hf}\f$).
909 * * 7: The recurrent-to-cell weights (\f$W_{hc}\f$).
912 * * 8: The recurrent-to-output weights (\f$W_{ho}\f$).
915 * * 9: The cell-to-input weights (\f$W_{ci}\f$). Optional.
918 * * 10:The cell-to-forget weights (\f$W_{cf}\f$). Optional.
921 * * 11:The cell-to-output weights (\f$W_{co}\f$). Optional.
936 * * 16:The projection weights (\f$W_{proj}\f$). Optional.
1221 * * 1: weights.
1227 * [num_units, num_units], with columns corresponding to the weights
1339 * * ?weights_feature? is a weights matrix that processes the inputs (by
1343 * * ?weights_time? is a weights matrix that processes the ?memory? (by a
1350 * Each rank adds a dimension to the weights matrices by means of stacking
