Training decision trees as replacement for convolution layers

Wolfgang Fuhl, Gjergji Kasneci, Wolfgang Rosenstiel, Enkeljda Kasneci

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

3 Zitate (Scopus)

Abstract

We present an alternative layer to convolution layers in convolutional neural networks (CNNs). Our approach reduces the complexity of convolutions by replacing it with binary decisions. Those binary decisions are used as indexes to conditional distributions where each weight represents a leaf in a decision tree. This means that only the indices to the weights need to be determined once, thus reducing the complexity of convolutions by the depth of the output tensor. Index computation is performed by simple binary decisions that require fewer cycles compared to conventionally used multiplications. In addition, we show how convolutions can be replaced by binary decisions. These binary decisions form indices in the conditional distributions and we show how they are used to replace 2D weight matrices as well as 3D weight tensors. These new layers can be trained like convolution layers in CNNs based on the backpropagation algorithm, for which we provide a formalization. Our results on multiple publicly available data sets show that our approach performs similar to conventional neuronal networks. Beyond the formalized reduction of complexity and the improved qualitative performance, we show the runtime improvement empirically compared to convolution layers.

OriginalspracheEnglisch
TitelAAAI 2020 - 34th AAAI Conference on Artificial Intelligence
Herausgeber (Verlag)AAAI Press
Seiten3882-3889
Seitenumfang8
ISBN (elektronisch)9781577358350
PublikationsstatusVeröffentlicht - 2020
Extern publiziertJa
Veranstaltung34th AAAI Conference on Artificial Intelligence, AAAI 2020 - New York, USA/Vereinigte Staaten
Dauer: 7 Feb. 202012 Feb. 2020

Publikationsreihe

NameAAAI 2020 - 34th AAAI Conference on Artificial Intelligence

Konferenz

Konferenz34th AAAI Conference on Artificial Intelligence, AAAI 2020
Land/GebietUSA/Vereinigte Staaten
OrtNew York
Zeitraum7/02/2012/02/20

Fingerprint

Untersuchen Sie die Forschungsthemen von „Training decision trees as replacement for convolution layers“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren