Examples of NNRandomInitializer

com.github.neuralnetworks.training.random.NNRandomInitializer
Random Initializer for neural networks weights - all the connections between neurons are traversed and initialized

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  MnistInputProvider trainInputProvider = new MnistInputProvider("train-images.idx3-ubyte", "train-labels.idx1-ubyte", 1, 2, new MnistTargetMultiNeuronOutputConverter());
  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1000, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f);


  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));


  Environment.getInstance().setExecutionMode(EXECUTION_MODE.CPU);

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  MnistInputProvider trainInputProvider = new MnistInputProvider("train-images.idx3-ubyte", "train-labels.idx1-ubyte", 1, 1, new MnistTargetMultiNeuronOutputConverter());
  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1000, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  AparapiCDTrainer t = TrainerFactory.cdSigmoidTrainer(rbm, trainInputProvider, testInputProvider,  new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 1, false);


  t.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));
  Environment.getInstance().setExecutionMode(EXECUTION_MODE.CPU);
  t.train();
  t.test();

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  MnistInputProvider trainInputProvider = new MnistInputProvider("train-images.idx3-ubyte", "train-labels.idx1-ubyte", 1, 1, new MnistTargetMultiNeuronOutputConverter());
  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1000, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  Trainer<?> t = TrainerFactory.backPropagationAutoencoder(nn, trainInputProvider, testInputProvider,  new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 0f);


  t.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));
  Environment.getInstance().setExecutionMode(EXECUTION_MODE.CPU);
  t.train();
  nn.removeLayer(nn.getOutputLayer());

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1000, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  // Backpropagation trainer that also works for convolutional and subsampling layers
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(nn, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.01f, 0.5f, 0f, 0f);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));


  // cpu execution mode

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  // Backpropagation trainer that also works for convolutional and subsampling layers
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(nn, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.02f, 0.5f, 0f, 0f);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));


  // cpu execution

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  trainInputProvider.addInputModifier(new ScalingInputFunction(255));
  MnistInputProvider testInputProvider = new MnistInputProvider("t10k-images.idx3-ubyte", "t10k-labels.idx1-ubyte", 1, 1, new MnistTargetMultiNeuronOutputConverter());
  testInputProvider.addInputModifier(new ScalingInputFunction(255));


  // Backpropagation trainer that also works for convolutional and subsampling layers
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(nn, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.02f, 0.5f, 0f, 0f);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName(), false, true));


  // cpu execution

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  IrisInputProvider testInputProvider = new IrisInputProvider(new IrisTargetMultiNeuronOutputConverter(), false);
  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));
  OutputError outputError = new MultipleNeuronsOutputError();


  // trainer
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, outputError, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f, 0f, 150, 1, 2000);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName()));


  // early stopping

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));


  OutputError outputError = new MultipleNeuronsOutputError();


  // trainer
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(mlp, trainInputProvider, testInputProvider, outputError, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f), 0.5f), 0.02f, 0.7f, 0f, 0f, 0f, 150, 1, 2000);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName()));


  // early stopping

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer

  IrisInputProvider testInputProvider = new IrisInputProvider(new IrisTargetMultiNeuronOutputConverter(), false);
  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));
  MultipleNeuronsOutputError error = new MultipleNeuronsOutputError();


  // trainers
  AparapiCDTrainer t = TrainerFactory.cdSigmoidBinaryTrainer(rbm, trainInputProvider, testInputProvider, error, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 1, 1, 100, true);


  // log data
  t.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName()));


  // training

View Full Code Here

Examples of com.github.neuralnetworks.training.random.NNRandomInitializer


  IrisInputProvider testInputProvider = new IrisInputProvider(new IrisTargetMultiNeuronOutputConverter(), false);
  testInputProvider.addInputModifier(new ScalingInputFunction(testInputProvider));


  // rbm trainers for each layer
  AparapiCDTrainer firstTrainer = TrainerFactory.cdSigmoidBinaryTrainer(dbn.getFirstNeuralNetwork(), null, null, null, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 1, 150, 1000, true);
  AparapiCDTrainer lastTrainer = TrainerFactory.cdSigmoidBinaryTrainer(dbn.getLastNeuralNetwork(), null, null, null, new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 1, 150, 1000, true);


  Map<NeuralNetwork, OneStepTrainer<?>> map = new HashMap<>();
  map.put(dbn.getFirstNeuralNetwork(), firstTrainer);
  map.put(dbn.getLastNeuralNetwork(), lastTrainer);


  // deep trainer
  DBNTrainer deepTrainer = TrainerFactory.dbnTrainer(dbn, map, trainInputProvider, null, null);


  Environment.getInstance().setExecutionMode(EXECUTION_MODE.SEQ);


  // layer pre-training
  deepTrainer.train();


  // fine tuning backpropagation
  BackPropagationTrainer<?> bpt = TrainerFactory.backPropagation(dbn, trainInputProvider, testInputProvider, new MultipleNeuronsOutputError(), new NNRandomInitializer(new MersenneTwisterRandomInitializer(-0.01f, 0.01f)), 0.01f, 0.5f, 0f, 0f, 0f, 150, 150, 1000);


  // log data
  bpt.addEventListener(new LogTrainingListener(Thread.currentThread().getStackTrace()[1].getMethodName()));


  // training

View Full Code Here

0 1 2 3

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.