DeepLearningModel.DeepLearningParameters (h2o-algos version 3.12.0.1 API)

java.lang.Object
- water.Iced<hex.Model.Parameters>
- - hex.Model.Parameters
  - - hex.deeplearning.DeepLearningModel.DeepLearningParameters

All Implemented Interfaces:

java.io.Externalizable, java.io.Serializable, java.lang.Cloneable, water.Freezable<hex.Model.Parameters>

Enclosing class:

DeepLearningModel
```
public static class DeepLearningModel.DeepLearningParameters
extends hex.Model.Parameters
```
Deep Learning Parameters

See Also:
Serialized Form

Nested Class Summary

Nested Classes
Modifier and Type	Class and Description
`static class`	`DeepLearningModel.DeepLearningParameters.Activation` Activation functions
`static class`	`DeepLearningModel.DeepLearningParameters.ClassSamplingMethod`
`static class`	`DeepLearningModel.DeepLearningParameters.InitialWeightDistribution`
`static class`	`DeepLearningModel.DeepLearningParameters.Loss` Loss functions Absolute, Quadratic, Huber, Quantile for regression Quadratic, ModifiedHuber or CrossEntropy for classification
`static class`	`DeepLearningModel.DeepLearningParameters.MissingValuesHandling`

Nested classes/interfaces inherited from class hex.Model.Parameters
hex.Model.Parameters.CategoricalEncodingScheme, hex.Model.Parameters.FoldAssignmentScheme

Field Summary

Fields
Modifier and Type	Field and Description
`DeepLearningModel.DeepLearningParameters.Activation`	`_activation` The activation function (non-linearity) to be used the neurons in the hidden layers.
`boolean`	`_adaptive_rate` The implemented adaptive learning rate algorithm (ADADELTA) automatically combines the benefits of learning rate annealing and momentum training to avoid slow convergence.
`boolean`	`_autoencoder`
`double`	`_average_activation`
`double`	`_classification_stop` The stopping criteria in terms of classification error (1-accuracy) on the training data scoring dataset.
`boolean`	`_col_major`
`boolean`	`_diagnostics` Gather diagnostics for hidden layers, such as mean and RMS values of learning rate, momentum, weights and biases.
`boolean`	`_elastic_averaging`
`double`	`_elastic_averaging_moving_rate`
`double`	`_elastic_averaging_regularization`
`double`	`_epochs` The number of passes over the training dataset to be carried out.
`double`	`_epsilon` The second of two hyper parameters for adaptive learning rate (ADADELTA).
`boolean`	`_export_weights_and_biases`
`boolean`	`_fast_mode` Enable fast mode (minor approximation in back-propagation), should not affect results significantly.
`boolean`	`_force_load_balance` Increase training speed on small datasets by splitting it into many chunks to allow utilization of all cores.
`int[]`	`_hidden` The number and size of each hidden layer in the model.
`double[]`	`_hidden_dropout_ratios` A fraction of the inputs for each hidden layer to be omitted from training in order to improve generalization.
`water.Key[]`	`_initial_biases` Frame keys for initial bias vectors
`DeepLearningModel.DeepLearningParameters.InitialWeightDistribution`	`_initial_weight_distribution` The distribution from which initial weights are to be drawn.
`double`	`_initial_weight_scale` The scale of the distribution function for Uniform or Normal distributions.
`water.Key[]`	`_initial_weights` Frame keys for initial weight matrices
`double`	`_input_dropout_ratio` A fraction of the features for each training row to be omitted from training in order to improve generalization (dimension sampling).
`double`	`_l1` A regularization method that constrains the absolute value of the weights and has the net effect of dropping some weights (setting them to zero) from a model to reduce complexity and avoid overfitting.
`double`	`_l2` A regularization method that constrains the sum of the squared weights.
`DeepLearningModel.DeepLearningParameters.Loss`	`_loss` The loss (error) function to be minimized by the model.
`int`	`_max_categorical_features` Max.
`float`	`_max_w2` A maximum on the sum of the squared incoming weights into any one neuron.
`int`	`_mini_batch_size`
`DeepLearningModel.DeepLearningParameters.MissingValuesHandling`	`_missing_values_handling`
`double`	`_momentum_ramp` The momentum_ramp parameter controls the amount of learning for which momentum increases (assuming momentum_stable is larger than momentum_start).
`double`	`_momentum_stable` The momentum_stable parameter controls the final momentum value reached after momentum_ramp training samples.
`double`	`_momentum_start` The momentum_start parameter controls the amount of momentum at the beginning of training.
`boolean`	`_nesterov_accelerated_gradient` The Nesterov accelerated gradient descent method is a modification to traditional gradient descent for convex functions.
`boolean`	`_overwrite_with_best_model` If enabled, store the best model under the destination key of this model at the end of training.
`boolean`	`_quiet_mode` Enable quiet mode for less output to standard output.
`double`	`_rate` When adaptive learning rate is disabled, the magnitude of the weight updates are determined by the user specified learning rate (potentially annealed), and are a function of the difference between the predicted value and the target value.
`double`	`_rate_annealing` Learning rate annealing reduces the learning rate to "freeze" into local minima in the optimization landscape.
`double`	`_rate_decay` The learning rate decay parameter controls the change of learning rate across layers.
`double`	`_regression_stop` The stopping criteria in terms of regression error (MSE) on the training data scoring dataset.
`boolean`	`_replicate_training_data` Replicate the entire training dataset onto every node for faster training on small datasets.
`boolean`	`_reproducible` Force reproducibility on small data (will be slow - only uses 1 thread)
`double`	`_rho` The first of two hyper parameters for adaptive learning rate (ADADELTA).
`double`	`_score_duty_cycle` Maximum fraction of wall clock time spent on model scoring on training and validation samples, and on diagnostics such as computation of feature importances (i.e., not on training).
`double`	`_score_interval` The minimum time (in seconds) to elapse between model scoring.
`long`	`_score_training_samples` The number of training dataset points to be used for scoring.
`long`	`_score_validation_samples` The number of validation dataset points to be used for scoring.
`DeepLearningModel.DeepLearningParameters.ClassSamplingMethod`	`_score_validation_sampling` Method used to sample the validation dataset for scoring, see Score Validation Samples above.
`boolean`	`_shuffle_training_data` Enable shuffling of training data (on each node).
`boolean`	`_single_node_mode` Run on a single node for fine-tuning of model parameters.
`boolean`	`_sparse`
`double`	`_sparsity_beta`
`boolean`	`_standardize` If enabled, automatically standardize the data.
`double`	`_target_ratio_comm_to_comp`
`long`	`_train_samples_per_iteration` The number of training data rows to be processed per iteration.
`boolean`	`_use_all_factor_levels`
`boolean`	`_variable_importances` Whether to compute variable importances for input features.

Fields inherited from class hex.Model.Parameters
_auto_rebalance, _balance_classes, _categorical_encoding, _checkpoint, _class_sampling_factors, _distribution, _fold_assignment, _fold_column, _huber_alpha, _ignore_const_cols, _ignored_columns, _is_cv_model, _keep_cross_validation_fold_assignment, _keep_cross_validation_predictions, _max_after_balance_size, _max_categorical_levels, _max_confusion_matrix_size, _max_runtime_secs, _nfolds, _offset_column, _parallelize_cross_validation, _pretrained_autoencoder, _quantile_alpha, _response_column, _score_each_iteration, _seed, _stopping_metric, _stopping_rounds, _stopping_tolerance, _train, _tweedie_power, _valid, _weights_column, MAX_SUPPORTED_LEVELS

Constructor Summary

Constructors
Constructor and Description

DeepLearningModel.DeepLearningParameters()

Constructors
Constructor and Description
`DeepLearningModel.DeepLearningParameters()`

Method Summary

Methods
Modifier and Type	Method and Description
`java.lang.String`	`algoName()`
`protected double`	`defaultStoppingTolerance()`
`java.lang.String`	`fullName()`
`java.lang.String`	`javaName()`
`double`	`missingColumnsType()`
`long`	`progressUnits()`

Methods inherited from class hex.Model.Parameters
checksum_impl, checksum, defaultDropConsCols, getOrMakeRealSeed, hasCheckpoint, read_lock_frames, read_unlock_frames, setTrain, train, valid

Methods inherited from class water.Iced
asBytes, clone, copyOver, frozenType, read, readExternal, readJSON, reloadFromBytes, toJsonString, write, writeExternal, writeJSON

Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - _overwrite_with_best_model
```
public boolean _overwrite_with_best_model
```
    If enabled, store the best model under the destination key of this model at the end of training. Only applicable if training is not cancelled.
  - _autoencoder
```
public boolean _autoencoder
```
  - _use_all_factor_levels
```
public boolean _use_all_factor_levels
```
  - _standardize
```
public boolean _standardize
```
    If enabled, automatically standardize the data. If disabled, the user must provide properly scaled input data.
  - _activation
```
public DeepLearningModel.DeepLearningParameters.Activation _activation
```
    The activation function (non-linearity) to be used the neurons in the hidden layers. Tanh: Hyperbolic tangent function (same as scaled and shifted sigmoid). Rectifier: Chooses the maximum of (0, x) where x is the input value. Maxout: Choose the maximum coordinate of the input vector. With Dropout: Zero out a random user-given fraction of the incoming weights to each hidden layer during training, for each training row. This effectively trains exponentially many models at once, and can improve generalization.
  - _hidden
```
public int[] _hidden
```
    The number and size of each hidden layer in the model. For example, if a user specifies "100,200,100" a model with 3 hidden layers will be produced, and the middle hidden layer will have 200 neurons.
  - _epochs
```
public double _epochs
```
    The number of passes over the training dataset to be carried out. It is recommended to start with lower values for initial experiments. This value can be modified during checkpoint restarts and allows continuation of selected models.
  - _train_samples_per_iteration
```
public long _train_samples_per_iteration
```
    The number of training data rows to be processed per iteration. Note that independent of this parameter, each row is used immediately to update the model with (online) stochastic gradient descent. This parameter controls the synchronization period between nodes in a distributed environment and the frequency at which scoring and model cancellation can happen. For example, if it is set to 10,000 on H2O running on 4 nodes, then each node will process 2,500 rows per iteration, sampling randomly from their local data. Then, model averaging between the nodes takes place, and scoring can happen (dependent on scoring interval and duty factor). Special values are 0 for one epoch per iteration, -1 for processing the maximum amount of data per iteration (if **replicate training data** is enabled, N epochs will be trained per iteration on N nodes, otherwise one epoch). Special value of -2 turns on automatic mode (auto-tuning).
  - _target_ratio_comm_to_comp
```
public double _target_ratio_comm_to_comp
```
  - _adaptive_rate
```
public boolean _adaptive_rate
```
    The implemented adaptive learning rate algorithm (ADADELTA) automatically combines the benefits of learning rate annealing and momentum training to avoid slow convergence. Specification of only two parameters (rho and epsilon) simplifies hyper parameter search. In some cases, manually controlled (non-adaptive) learning rate and momentum specifications can lead to better results, but require the specification (and hyper parameter search) of up to 7 parameters. If the model is built on a topology with many local minima or long plateaus, it is possible for a constant learning rate to produce sub-optimal results. Learning rate annealing allows digging deeper into local minima, while rate decay allows specification of different learning rates per layer. When the gradient is being estimated in a long valley in the optimization landscape, a large learning rate can cause the gradient to oscillate and move in the wrong direction. When the gradient is computed on a relatively flat surface with small learning rates, the model can converge far slower than necessary.
  - _rho
```
public double _rho
```
    The first of two hyper parameters for adaptive learning rate (ADADELTA). It is similar to momentum and relates to the memory to prior weight updates. Typical values are between 0.9 and 0.999. This parameter is only active if adaptive learning rate is enabled.
  - _epsilon
```
public double _epsilon
```
    The second of two hyper parameters for adaptive learning rate (ADADELTA). It is similar to learning rate annealing during initial training and momentum at later stages where it allows forward progress. Typical values are between 1e-10 and 1e-4. This parameter is only active if adaptive learning rate is enabled.
  - _rate
```
public double _rate
```
    When adaptive learning rate is disabled, the magnitude of the weight updates are determined by the user specified learning rate (potentially annealed), and are a function of the difference between the predicted value and the target value. That difference, generally called delta, is only available at the output layer. To correct the output at each hidden layer, back propagation is used. Momentum modifies back propagation by allowing prior iterations to influence the current update. Using the momentum parameter can aid in avoiding local minima and the associated instability. Too much momentum can lead to instabilities, that's why the momentum is best ramped up slowly. This parameter is only active if adaptive learning rate is disabled.
  - _rate_annealing
```
public double _rate_annealing
```
    Learning rate annealing reduces the learning rate to "freeze" into local minima in the optimization landscape. The annealing rate is the inverse of the number of training samples it takes to cut the learning rate in half (e.g., 1e-6 means that it takes 1e6 training samples to halve the learning rate). This parameter is only active if adaptive learning rate is disabled.
  - _rate_decay
```
public double _rate_decay
```
    The learning rate decay parameter controls the change of learning rate across layers. For example, assume the rate parameter is set to 0.01, and the rate_decay parameter is set to 0.5. Then the learning rate for the weights connecting the input and first hidden layer will be 0.01, the learning rate for the weights connecting the first and the second hidden layer will be 0.005, and the learning rate for the weights connecting the second and third hidden layer will be 0.0025, etc. This parameter is only active if adaptive learning rate is disabled.
  - _momentum_start
```
public double _momentum_start
```
    The momentum_start parameter controls the amount of momentum at the beginning of training. This parameter is only active if adaptive learning rate is disabled.
  - _momentum_ramp
```
public double _momentum_ramp
```
    The momentum_ramp parameter controls the amount of learning for which momentum increases (assuming momentum_stable is larger than momentum_start). The ramp is measured in the number of training samples. This parameter is only active if adaptive learning rate is disabled.
  - _momentum_stable
```
public double _momentum_stable
```
    The momentum_stable parameter controls the final momentum value reached after momentum_ramp training samples. The momentum used for training will remain the same for training beyond reaching that point. This parameter is only active if adaptive learning rate is disabled.
  - _nesterov_accelerated_gradient
```
public boolean _nesterov_accelerated_gradient
```
    The Nesterov accelerated gradient descent method is a modification to traditional gradient descent for convex functions. The method relies on gradient information at various points to build a polynomial approximation that minimizes the residuals in fewer iterations of the descent.
  - _input_dropout_ratio
```
public double _input_dropout_ratio
```
    A fraction of the features for each training row to be omitted from training in order to improve generalization (dimension sampling).
  - _hidden_dropout_ratios
```
public double[] _hidden_dropout_ratios
```
    A fraction of the inputs for each hidden layer to be omitted from training in order to improve generalization. Defaults to 0.5 for each hidden layer if omitted.
  - _l1
```
public double _l1
```
    A regularization method that constrains the absolute value of the weights and has the net effect of dropping some weights (setting them to zero) from a model to reduce complexity and avoid overfitting.
  - _l2
```
public double _l2
```
    A regularization method that constrains the sum of the squared weights. This method introduces bias into parameter estimates, but frequently produces substantial gains in modeling as estimate variance is reduced.
  - _max_w2
```
public float _max_w2
```
    A maximum on the sum of the squared incoming weights into any one neuron. This tuning parameter is especially useful for unbound activation functions such as Rectifier.
  - _initial_weight_distribution
```
public DeepLearningModel.DeepLearningParameters.InitialWeightDistribution _initial_weight_distribution
```
    The distribution from which initial weights are to be drawn. The default option is an optimized initialization that considers the size of the network. The "uniform" option uses a uniform distribution with a mean of 0 and a given interval. The "normal" option draws weights from the standard normal distribution with a mean of 0 and given standard deviation.
  - _initial_weight_scale
```
public double _initial_weight_scale
```
    The scale of the distribution function for Uniform or Normal distributions. For Uniform, the values are drawn uniformly from -initial_weight_scale...initial_weight_scale. For Normal, the values are drawn from a Normal distribution with a standard deviation of initial_weight_scale.
  - _initial_weights
```
public water.Key[] _initial_weights
```
    Frame keys for initial weight matrices
  - _initial_biases
```
public water.Key[] _initial_biases
```
    Frame keys for initial bias vectors
  - _loss
```
public DeepLearningModel.DeepLearningParameters.Loss _loss
```
    The loss (error) function to be minimized by the model. Cross Entropy loss is used when the model output consists of independent hypotheses, and the outputs can be interpreted as the probability that each hypothesis is true. Cross entropy is the recommended loss function when the target values are class labels, and especially for imbalanced data. It strongly penalizes error in the prediction of the actual class label. Mean Square loss is used when the model output are continuous real values, but can be used for classification as well (where it emphasizes the error on all output classes, not just for the actual class).
  - _score_interval
```
public double _score_interval
```
    The minimum time (in seconds) to elapse between model scoring. The actual interval is determined by the number of training samples per iteration and the scoring duty cycle.
  - _score_training_samples
```
public long _score_training_samples
```
    The number of training dataset points to be used for scoring. Will be randomly sampled. Use 0 for selecting the entire training dataset.
  - _score_validation_samples
```
public long _score_validation_samples
```
    The number of validation dataset points to be used for scoring. Can be randomly sampled or stratified (if "balance classes" is set and "score validation sampling" is set to stratify). Use 0 for selecting the entire training dataset.
  - _score_duty_cycle
```
public double _score_duty_cycle
```
    Maximum fraction of wall clock time spent on model scoring on training and validation samples, and on diagnostics such as computation of feature importances (i.e., not on training).
  - _classification_stop
```
public double _classification_stop
```
    The stopping criteria in terms of classification error (1-accuracy) on the training data scoring dataset. When the error is at or below this threshold, training stops.
  - _regression_stop
```
public double _regression_stop
```
    The stopping criteria in terms of regression error (MSE) on the training data scoring dataset. When the error is at or below this threshold, training stops.
  - _quiet_mode
```
public boolean _quiet_mode
```
    Enable quiet mode for less output to standard output.
  - _score_validation_sampling
```
public DeepLearningModel.DeepLearningParameters.ClassSamplingMethod _score_validation_sampling
```
    Method used to sample the validation dataset for scoring, see Score Validation Samples above.
  - _diagnostics
```
public boolean _diagnostics
```
    Gather diagnostics for hidden layers, such as mean and RMS values of learning rate, momentum, weights and biases.
  - _variable_importances
```
public boolean _variable_importances
```
    Whether to compute variable importances for input features. The implemented method (by Gedeon) considers the weights connecting the input features to the first two hidden layers.
  - _fast_mode
```
public boolean _fast_mode
```
    Enable fast mode (minor approximation in back-propagation), should not affect results significantly.
  - _force_load_balance
```
public boolean _force_load_balance
```
    Increase training speed on small datasets by splitting it into many chunks to allow utilization of all cores.
  - _replicate_training_data
```
public boolean _replicate_training_data
```
    Replicate the entire training dataset onto every node for faster training on small datasets.
  - _single_node_mode
```
public boolean _single_node_mode
```
    Run on a single node for fine-tuning of model parameters. Can be useful for checkpoint resumes after training on multiple nodes for fast initial convergence.
  - _shuffle_training_data
```
public boolean _shuffle_training_data
```
    Enable shuffling of training data (on each node). This option is recommended if training data is replicated on N nodes, and the number of training samples per iteration is close to N times the dataset size, where all nodes train with (almost) all the data. It is automatically enabled if the number of training samples per iteration is set to -1 (or to N times the dataset size or larger).
  - _missing_values_handling
```
public DeepLearningModel.DeepLearningParameters.MissingValuesHandling _missing_values_handling
```
  - _sparse
```
public boolean _sparse
```
  - _col_major
```
public boolean _col_major
```
  - _average_activation
```
public double _average_activation
```
  - _sparsity_beta
```
public double _sparsity_beta
```
  - _max_categorical_features
```
public int _max_categorical_features
```
    Max. number of categorical features, enforced via hashing (Experimental)
  - _reproducible
```
public boolean _reproducible
```
    Force reproducibility on small data (will be slow - only uses 1 thread)
  - _export_weights_and_biases
```
public boolean _export_weights_and_biases
```
  - _elastic_averaging
```
public boolean _elastic_averaging
```
  - _elastic_averaging_moving_rate
```
public double _elastic_averaging_moving_rate
```
  - _elastic_averaging_regularization
```
public double _elastic_averaging_regularization
```
  - _mini_batch_size
```
public int _mini_batch_size
```
- Constructor Detail
  - DeepLearningModel.DeepLearningParameters
```
public DeepLearningModel.DeepLearningParameters()
```
- Method Detail
  - algoName
```
public java.lang.String algoName()
```
    Specified by:
    
    algoName in class hex.Model.Parameters
  - fullName
```
public java.lang.String fullName()
```
    Specified by:
    
    fullName in class hex.Model.Parameters
  - javaName
```
public java.lang.String javaName()
```
    Specified by:
    
    javaName in class hex.Model.Parameters
  - defaultStoppingTolerance
```
protected double defaultStoppingTolerance()
```
    Overrides:
    
    defaultStoppingTolerance in class hex.Model.Parameters
  - progressUnits
```
public long progressUnits()
```
    Specified by:
    
    progressUnits in class hex.Model.Parameters
  - missingColumnsType
```
public double missingColumnsType()
```
    Overrides:
    
    missingColumnsType in class hex.Model.Parameters

Class DeepLearningModel.DeepLearningParameters

Nested Class Summary

Nested classes/interfaces inherited from class hex.Model.Parameters

Field Summary

Fields inherited from class hex.Model.Parameters

Constructor Summary

Method Summary

Methods inherited from class hex.Model.Parameters

Methods inherited from class water.Iced

Methods inherited from class java.lang.Object

Field Detail

_overwrite_with_best_model

_autoencoder

_use_all_factor_levels

_standardize

_activation

_hidden

_epochs

_train_samples_per_iteration

_target_ratio_comm_to_comp

_adaptive_rate

_rho

_epsilon

_rate

_rate_annealing

_rate_decay

_momentum_start

_momentum_ramp

_momentum_stable

_nesterov_accelerated_gradient

_input_dropout_ratio

_hidden_dropout_ratios

_l1

_l2

_max_w2

_initial_weight_distribution

_initial_weight_scale

_initial_weights

_initial_biases

_loss

_score_interval

_score_training_samples

_score_validation_samples

_score_duty_cycle

_classification_stop

_regression_stop

_quiet_mode

_score_validation_sampling

_diagnostics

_variable_importances

_fast_mode

_force_load_balance

_replicate_training_data

_single_node_mode

_shuffle_training_data

_missing_values_handling

_sparse

_col_major

_average_activation

_sparsity_beta

_max_categorical_features

_reproducible

_export_weights_and_biases

_elastic_averaging

_elastic_averaging_moving_rate

_elastic_averaging_regularization

_mini_batch_size

Constructor Detail

DeepLearningModel.DeepLearningParameters

Method Detail

algoName

fullName

javaName

defaultStoppingTolerance

progressUnits

missingColumnsType