Abstract
In this contribution, we show how to incorporate prior knowledge to a deep neural network architecture in a principled manner. We enforce feature space invariances using a novel layer based on invariant integration. This allows us to construct a complete feature space invariant to finite transformation groups. We apply our proposed layer to explicitly insert invariance properties for vision-related classification tasks, demonstrate our approach for the case of rotation invariance and report state-of-the-art performance on the Rotated-MNIST dataset. Our method is especially beneficial when training with limited data.
Originalsprache | Englisch |
---|---|
Seiten | 103-108 |
Seitenumfang | 6 |
Publikationsstatus | Veröffentlicht - 10.2020 |
Veranstaltung | European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2020 - Brügge, Belgien Dauer: 02.10.2020 → 04.10.2020 |
Tagung, Konferenz, Kongress
Tagung, Konferenz, Kongress | European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2020 |
---|---|
Kurztitel | ESANN 2020 |
Land/Gebiet | Belgien |
Ort | Brügge |
Zeitraum | 02.10.20 → 04.10.20 |