Why biases are excluded from l2_regularization term?

Issue #133 new
Alireza Khorshidi created an issue

Why l2_regularization = tf.reduce_sum(tf.square(W_fc)) and not l2_regularization =tf.reduce_sum(tf.square(W_fc))+tf.reduce_sum(tf.square(b_fc)) here?

Comments (2)

  1. Log in to comment