Packages

trait DeepLearningSupport extends Logging

Support class to create and train Deep Learning Model

Annotations
@Deprecated
Linear Supertypes
Logging, Serializable, Serializable, Logging, AnyRef, Any
Known Subclasses
DeepLearningSupport
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. DeepLearningSupport
  2. Logging
  3. Serializable
  4. Serializable
  5. Logging
  6. AnyRef
  7. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Value Members

  1. def DLModel[T <: Frame](train: T, valid: T, response: String, modelId: String = "model", epochs: Int = 10, l1: Double = 0.0001, l2: Double = 0.0001, activation: Activation = Activation.RectifierWithDropout, hidden: Array[Int] = Array(200, 200)): DeepLearningModel

    Create Deep Learning Model for the basic usage.

    Create Deep Learning Model for the basic usage. This method exposes the basic configuration of the model. If you need to specify some arguments which are not exposed, please use the DeepLearning model via Sparkling Water pipelines API or using the raw java API

    T

    H2O Frame Type

    train

    frame to train

    valid

    validation frame

    response

    response column

    modelId

    name of the model

    epochs

    number of epochs

    l1

    l1 regularization

    l2

    l2 regularization

    activation

    activation function

    hidden

    number and size of the hidden layers

    returns

    Deep Learning Model

    Annotations
    @DeprecatedMethod( ... , "3.32" )