fitness: Fit and validate neural network

In c7rishi/hidgenclassifier: Functions for Bayesian hierarchical hidden genome classifier

Fit and validate neural network

Description

Fit and validate neural network

Usage

fitness(
  X_train_norm,
  Y_train_onehot,
  X_val_norm,
  Y_val_onehot,
  learning_rate,
  weight_decay,
  dropout,
  num_dense_layers,
  num_dense_nodes,
  activation,
  epochs = 50,
  batch_size = 128,
  verbose = 0,
  seed = NULL
)

Arguments

X_train_norm	Normalized input matrix for training set
Y_train_onehot	One-hot representation of response for training set
X_val_norm	Normalized input matrix for validation set
Y_val_onehot	One-hot representation of response for validation set
epochs	Number of training epochs
batch_size	Batch size
verbose	Keras verbosity mode (0 = silent, 1 = progress bar, 2 = one line per epoch)

Value

Validation accuracy

c7rishi/hidgenclassifier documentation built on June 14, 2024, 11:10 a.m.