Why is the learning rate for the bias usually twice as large as the the LR for the weights?

3 Ansichten (letzte 30 Tage)
Salma Hassan
Salma Hassan am 3 Jan. 2018
Bearbeitet: Image Analyst am 5 Jan. 2018
Why is the learning rate for the bias usually twice as large as the the LR for the weights?
  2 Kommentare
Salma Hassan
Salma Hassan am 5 Jan. 2018
Bearbeitet: Image Analyst am 5 Jan. 2018
https://datascience.stackexchange.com/questions/23549/why-is-the-learning-rate-for-the-bias-usually-twice-as-large-as-the-the-lr-for-t
on the other hand if you check, for example alexnet layers you will find that net.Layers(N, 1).BiasLearnRateFactor=2 and net.Layers(N, 1).WeightLearnRateFactor = 1

Melden Sie sich an, um zu kommentieren.

Melden Sie sich an, um diese Frage zu beantworten.

Antworten (0)

Kategorien

Mehr zu Image Data Workflows finden Sie in Help Center und File Exchange

Tags

Produkte

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by