November 2019
Intermediate to advanced
304 pages
8h 40m
English
Content preview from Java Deep Learning Cookbook
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,
Start your free trial
How to do it...
- Configure the neural network with default configurations:
NeuralNetConfiguration.Builder neuralNetConfigBuilder = new NeuralNetConfiguration.Builder(); neuralNetConfigBuilder.seed(123); neuralNetConfigBuilder.weightInit(WeightInit.XAVIER); neuralNetConfigBuilder.updater(new Nadam()); neuralNetConfigBuilder.gradientNormalization(GradientNormalization.ClipElementWiseAbsoluteValue); neuralNetConfigBuilder.gradientNormalizationThreshold(0.5);
- Specify the input layer labels by calling addInputs():
ComputationGraphConfiguration.GraphBuilder compGraphBuilder = neuralNetConfigBuilder.graphBuilder(); compGraphBuilder.addInputs("trainFeatures");
- Add an LSTM layer using the addLayer() method:
compGraphBuilder.addLayer("L1", new ...