X hits on this document

211 views

0 shares

0 downloads

0 comments

7 / 57

Scaling

However we are asking a lot of the network to cope with these different ranges.

We are initially starting training by telling network that one variable is thousands of times more important than the other

Network will probably find correct weights, but why not make its task easier? - by giving it data scaled in such a way that all the weights can remain in small, similar, predictable ranges.

Document info
Document views211
Page views211
Page last viewedSat Jan 21 20:16:20 UTC 2017
Pages57
Paragraphs343
Words2583

Comments