= Klaus Greff
{c}
<Klaus Greff> is a <machine learning> researcher whose work includes controlled comparisons of <long short-term memory> architectures. His author homepage identifies the researcher and links his publications; the original byline of <LSTM: A Search Space Odyssey by Klaus Greff and others> confirms his participation in that study.<Klaus Greff homepage>[Author identification and research/publication links]{ref}
The study compared eight architectural variants across three task families, optimizing <hyperparameters> separately for each variant. This matters because a poorly tuned variant is not a fair test of its architecture. None significantly improved on the standard architecture in the reported comparisons, while removing particular components exposed the importance of the <LSTM forget gate> and output activation.<LSTM: A Search Space Odyssey by Klaus Greff and others>[Abstract: variant comparisons, separate tuning and component importance]{ref}
For an illustrative <ablation study>, compare a complete <recurrent neural network> with a version lacking one gate, while keeping the training task and evaluation procedure comparable. A worse result after removal is evidence about that component under the tested conditions; it does not establish that no alternative architecture could ever replace it. This is the scientific value of a controlled comparison beyond displaying one successful network.
\Image[https://qwlouse.github.io/images/portrait.jpg]
{title=Klaus Greff, identified on his author homepage}
{description=External portrait linked and labeled by <Klaus Greff homepage>.}
Back to article page
