deeplearning4j/deeplearning4j-examples

Increasing errors with MultiLayerNetworkExternalErrors.java Example

Ouverte

#914 ouverte le 18 oct. 2019

 (1 commentaire) (0 réaction) (0 personne assignée)Java (1 841 forks)batch import
help wantedquestion

Métriques du dépôt

Stars
 (2 395 étoiles)
Métriques de merge PR
 (Aucune PR mergée en 30 j)

Description

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

Guide contributeur