Why there is no bias and coefficient trainable parameters in the Max- and Average-Pooling Layers?

8 Ansichten (letzte 30 Tage)
For many Network, there are 2 trainable parameters in Polling Layers: Bias and Coefficient
Y=Coefficient*Max(X)+Bias;
Why the Matlab Layer doesn't support it? Are those 2 parameters not very useful for the final performance?

Antworten (1)

Sailesh Sidhwani
Sailesh Sidhwani am 28 Jul. 2017
Hi Lingjun,
Based on the MATLAB documentation, max-pooling and average-pooling layers does not perform any learning and are only used for down-sampling the data. Refer to the the section "More About" in the following documentation pages:
  1 Kommentar
LINGJUN KONG
LINGJUN KONG am 29 Jul. 2017
Is that because of that, the parameters are not very useful for the downsampling layer? I've seen that there are 2 trainable parameters in the LeNet-5

Melden Sie sich an, um zu kommentieren.

Kategorien

Mehr zu 图像深度学习 finden Sie in Help Center und File Exchange

Community Treasure Hunt

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

Start Hunting!