deep_lm: Deep Learning Regression with Automated Parameter Tuning

In tianwei-zhang/easyAI: Democratize AI

Description

Deep Learning Regression with Automated Parameter Tuning

Usage

deep_lm(x, y, option, num_layer = seq(1, 5, 1), max_units = NULL,
  start_unit = 5, max_dropout = 0.2, min_dropout = 0, max_lr = 0.2,
  min_lr = 0.001, iteration_per_layer = 5, validation_split = 0.2,
  num_epoch = 5, num_patience = 3, machine_type = "standard")

Arguments

x	training feature matrix
y	target matrix
option	either local or google for hyper-parameter tuning
num_layer	a vector of integers indicating the number of hidden layers to test. Default to seq(1,5,1)
max_units	the maximum number of hidden units in a layer. Default to an optimized value based on data
start_unit	the minimum number of hiddent units in a layer. Default to 5
max_dropout	A number between 0 and 1 indicating the maximum dropoff rate in a layer. Default to 0.2
min_dropout	A number between 0 and 1 indicating the minimum dropoff rate in a layer. Default to 0
max_lr	maximum learning rate in a run. Default to 0.2
min_lr	minimum learning rate in a run. Default to 0.001
iteration_per_layer	Number of parameter randomizations for a given number of hidden layers. More iterations will explore a larger parameter space
validation_split	Percent of data used for validation. Default to 20 percent
num_epoch	number of epoches to go through during training
num_patience	number of patience in early stopping criteria
machine_type	type of server to use. Could be standard, standard_gpu, standard_p100. For more visit https://cloud.google.com/ml-engine/docs/training-overview#machine_type_table

Value

returns a list object with two values:

• train_performance: A table with parameters and model performance metrics

• best_model: a keras_model object with the optimal structure

tianwei-zhang/easyAI documentation built on May 14, 2019, 12:48 p.m.