Subscription

Explore Products

Best Sellers

New Releases

Books

Videos

Audiobooks

Learning Hub

Conferences

Free Learning

You're reading from Java Deep Learning Cookbook Train neural networks for classification, NLP, and reinforcement learning using Deeplearning4j

Product type Paperback

Published in Nov 2019

Publisher Packt

ISBN-13 9781788995207

Length 304 pages

Edition 1st Edition

Languages

Java

Tools

Deeplearning4j

Concepts

Deep Learning

Author (1):

Rahul Raj

View More author details

Table of Contents (14) Chapters

Preface

1. Introduction to Deep Learning in Java

2. Data Extraction, Transformation, and Loading FREE CHAPTER

3. Building Deep Neural Networks for Binary Classification

4. Building Convolutional Neural Networks

5. Implementing Natural Language Processing

6. Constructing an LSTM Network for Time Series

7. Constructing an LSTM Neural Network for Sequence Classification

8. Performing Anomaly Detection on Unsupervised Data

9. Using RL4J for Reinforcement Learning

10. Developing Applications in a Distributed Environment

11. Applying Transfer Learning to Network Models

12. Benchmarking and Neural Network Optimization

13. Other Books You May Enjoy

Leave a review - let other readers know what you think

Configuring encoding thresholds

The DL4J Spark implementation makes use of a threshold encoding scheme to perform parameter updates across nodes in order to reduce the commuted message size across the network and thereby reduce the cost of traffic. The threshold encoding scheme introduces a new distributed training-specific hyperparameter called encoding threshold.

In this recipe, we will configure the threshold algorithm in a distributed training implementation.

How to do it...

Configure the threshold algorithm in SharedTrainingMaster:

TrainingMaster tm = new SharedTrainingMaster.Builder(voidConfiguration, minibatchSize)
   .thresholdAlgorithm(new AdaptiveThresholdAlgorithm(gradientThreshold))
  .build();

Configure the...

The rest of the chapter is locked

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $19.99/month. Cancel anytime

Authors (1)

Raj

Rahul Raj has more than 7 years of IT industry experience in software development, business analysis, client communication, and consulting on medium-/large-scale projects in multiple domains. Currently, he works as a lead software engineer in a top software development firm. He has extensive experience in development activities comprising requirement analysis, design, coding, implementation, code review, testing, user training, and enhancements. He has written a number of articles about neural networks in Java and they are featured by DL4J/ official Java community channels. He is also a certified machine learning professional, certified by Vskills, the largest government certification body in India.

See other products by Raj