uDreyfus2: Dataset uDreyfus2

In NNbenchmark: Datasets and Functions to Benchmark Neural Network Packages

Description

An univariate dataset (x, y) of class data.frame and dim 51 x 2 to be fitted by a neural network with 3 hidden neurons (10 parameters). This dataset was used to teach neural networks at ESPCI from 1991 to 2013. It usually appeared in the very first slides. This is a combination of 3 pure tanh() functions with a small noise. Due to the noise, the Jacobian matrix is not singular at the target parameter values. All algorithms should find the target parameter values.

References

Dreyfus, G., ESPCI https://www.neurones.espci.fr

Examples

ht(uDreyfus2)
plot(uDreyfus2)

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