The loss function serves as an evaluation of the training process, that is, how well the algorithm for generating synthetic data models the original data. The less loss, the more knowledge there is about the original data. To avoid overfitting, an early stop is usually implemented to terminate the training process as soon as the validation loss is no longer decreasing.
We use third-party web analytics tools to analyze website usage and measure the success of advertising campaigns. Cookies are set in the process and data is partly transferred to the USA. Further details can be found in our privacy policy. You can revoke or adjust your selection at any time under Settings.
Here you will find an overview of all cookies used. You can give your consent to whole categories or display further information and select certain cookies.