Skip to Main Content
Java Deep Learning Projects
book

Java Deep Learning Projects

by Md. Rezaul Karim
June 2018
Intermediate to advanced content levelIntermediate to advanced
436 pages
10h 33m
English
Packt Publishing
Content preview from Java Deep Learning Projects

Network construction

The following is a list of important hyperparameters and their details. Here, I will try to construct a five-layered CNN, as follows:

  • Layer 0 has a ConvolutionLayer having a 6 x 6 kernel, one channel (since they are grayscale images), a stride of 2 x 2, and 20 feature maps where ReLU is the activation function:
ConvolutionLayer layer_0 = new ConvolutionLayer.Builder(6,6)            .nIn(nChannels)            .stride(2,2) // default stride(2,2)            .nOut(20) // # of feature maps            .dropOut(0.7) // dropout to reduce overfitting            .activation(Activation.RELU) // Activation: rectified linear units            .build();
  • Layer 1 has SubsamplingLayer max pooling, and a stride of 2x2. Thus, by using stride, we down sample by a factor of 2. Note that only MAX, AVG, ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Java Deep Learning Essentials

Java Deep Learning Essentials

Yusuke Sugomori
Machine Learning in Java - Second Edition

Machine Learning in Java - Second Edition

AshishSingh Bhatia, Bostjan Kaluza
Mastering Java Machine Learning

Mastering Java Machine Learning

Uday Kamath, Krishna Choppella

Publisher Resources

ISBN: 9781788997454Supplemental Content