#deep_learning #foundations #initialization #lesso_9
Batch normalization (Ioffe & Szegedy (2015)), a technique that inserts layers into the the deep net that transform the output for the batch to be zero mean unit variance, has successfully facilitated training of the twenty-two layer GoogLeNet (Szegedy et al. (2015)). However, batch normalization adds a 30% computational overhead to each iteration.
If you want to change selection, open document below and click on "Move attachment"
- (no access) - All You Need is a Good Init ✔, p1
|status||not read|| ||reprioritisations|
|last reprioritisation on|| ||suggested re-reading day|
|started reading on|| ||finished reading on|