R-squared results of test and validation differ by a huge margin

Published: 5/10/2017
R-squared results of test and validation differ by a huge margin
Source: STACKOVERFLOW.COM

I am working on a regression problem with keras and tensorflow using a neural network. The data is split, so that 282774 datasets are for training, 70694 are for validation and 88367 are for testing. To evaluate my models I am printing out the mean squared error (MSE), the mean absolute error (MAE) and the R-squared score. These are some examples from the results I get: MSE MAE R-squared Training

Read more
Related news
Comment