mirror of
https://github.com/MartinThoma/LaTeX-examples.git
synced 2025-04-18 19:18:21 +02:00
8 lines
375 B
TeX
8 lines
375 B
TeX
\begin{abstract}
|
|
This paper reviews the most common activation functions for convolution neural
|
|
networks. They are evaluated on the Asirra, GTSRB, HASYv2, STL-10, CIFAR-10,
|
|
CIFAR-100 and MNIST dataset. Possible reasons for the differences in their
|
|
performance are given.
|
|
|
|
New state of the art results are achieved for Asirra, GTSRB, HASYv2 and STL-10.
|
|
\end{abstract}
|