NNbigdatasets: Big Datasets in One list (2020)

In NNbenchmark: Datasets and Functions to Benchmark Neural Network Packages

Description

NNbigdatasets is a list with the big datasets presented in this package and the recommended number of hidden neurons for each neural network model.

• bWoodN1: 5 neurons.

Each item of the list is itself a list with 5 components:

• ds: character. The name of the dataset.

• neur: integer. The recommanded number of hidden neurons in the NN model and in fmlaNN.

• nparNN: integer. The number of parameters in fmlaNN.

• fmlaNN: the formula of the corresponding neural network, with tanh() as the activation function in the hidden layer.

• Z: matrix or data.frame. The dataset itself.

Using attach() and detach() gives a direct access to these items.

Examples

ht(NNbigdatasets)

NNdataSummary(NNbigdatasets)

NNbenchmark documentation built on June 5, 2021, 5:06 p.m.