deeplearning4j/deeplearning4j-examples

Increasing errors with MultiLayerNetworkExternalErrors.java Example

Aperta

#914 aperta il 18 ott 2019

 (1 commento) (0 reazioni) (0 assegnatari)Java (1841 fork)batch import
help wantedquestion

Metriche repository

Star
 (2395 stelle)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

Hi,

I am trying to using train a simple 2 layer network on a simple synthetic dataset. With two features X1 and X2. and lables: y = X1^2 + X2^2

I am calculating the error for each epoch manually and using the errors to call backprop, similar to the MultiLayerNetworkExternalErrors.java example

The prediction error is increasing with each epoch, I would have expected decreasing errors with on this simple dataset. Could someone help me with if the issue is with how I am using dl4j methods ?

Code: https://gist.github.com/Saurabh7/9b5ea7def2a167903e7d206e272e2662 Data: https://gist.github.com/Saurabh7/982fb4ddfbd58bd866782ea31b95aef1

Guida contributor