Training Capsule Networks with Various Parameters (original) (raw)

2019 IEEE 13th International Symposium on Applied Computational Intelligence and Informatics (SACI)

Abstract

Nowadays convolutional neural networks (CNNs) have produced the state-of-the-art performance in image classification and segmentation tasks. The efficiency of the neural networks is one of the bests when the testing samples are close to the training data. Nevertheless, if we make some transformation on the dataset, the performance of the convolutional neural network reduced. Recently, capsule networks (CapsNet) have been introduced to solve some of the problems of neural networks. In this paper we examine the effectiveness of three different capsule based neural networks, and compare the performance when the parameters of the dynamic routing algorithm and the squashing function are modified.

Áron Ballagi hasn't uploaded this paper.

Let Áron know you want this paper to be uploaded.

Ask for this paper to be uploaded.