max_nodes

Maximum number of hidden layer nodes

Topics

surrogate_models

Specification

• Alias: nodes

• Arguments: INTEGER

• Default: numTrainingData - 1

Description

Limits the maximum number of hidden layer nodes in the neural network model. The default is to use one less node than the number of available training data points yielding a fully-determined linear least squares problem. However, reducing the number of nodes can help reduce overfitting and more importantly, can drastically reduce surrogate construction time when building from a large data set. (Historically, Dakota limited the number of nodes to 100.)

The keyword max_nodes provides an upper bound. Dakota’s orthogonal matching pursuit algorithm may further reduce the effective number of nodes in the final model to achieve better generalization to unseen points.