X hits on this document

154 views

0 shares

0 downloads

0 comments

34 / 57

Network outputs and error calculation

If output(s) should be categories (NN is a classifier), output(s) should be a logistic function trained by the error between output and target or a soft-max function with a cross-entropy error term should be calculated between outputs and targets

If output(s) should be real numbers (NN is performing regression), output(s) should be linear and a mean-square error term should be calculated between outputs and targets

Document info
Document views154
Page views154
Page last viewedFri Dec 09 16:11:30 UTC 2016
Pages57
Paragraphs343
Words2583

Comments