Skip to main content

Research Repository

Advanced Search

A convolutional Siamese network for developing similarity knowledge in the SelfBACK dataset.

Martin, Kyle; Wiratunga, Nirmalie; Sani, Sadiq; Massie, Stewart; Clos, Jérémie

Authors

Kyle Martin

Sadiq Sani

Jérémie Clos



Contributors

Antonio A. Sanchez-Ruiz
Editor

Anders Kofod-Petersen
Editor

Abstract

The Siamese Neural Network (SNN) is a neural network architecture capable of learning similarity knowledge between cases in a case base by receiving pairs of cases and analysing the differences between their features to map them to a multi-dimensional feature space. This paper demonstrates the development of a Convolutional Siamese Network (CSN) for the purpose of case similarity knowledge generation on the SelfBACK dataset. We also demonstrate a CSN is capable of performing classification on the SelfBACK dataset to an accuracy which is comparable with a standard Convolutional Neural Network.

Citation

MARTIN, K., WIRATUNGA, N., SANI, S., MASSIE, S. and CLOS, J. 2017. A convolutional Siamese network for developing similarity knowledge in the SelfBACK dataset. In Sanchez-Ruiz, A.A. and Kofod-Petersen, A. (eds.) Workshop proceedings of the 25th International conference on case-based reasoning (ICCBR 2017), 26-29 June 2017, Trondheim, Norway. CEUR workshop proceedings, 2028. Aachen: CEUR-WS [online], session 2: case-based reasoning and deep learning workshop (CBRDL-2017), pages 85-94. Available from: http://ceur-ws.org/Vol-2028/paper8.pdf

Conference Name 25th International conference on case-based reasoning (ICCBR 2017)
Start Date Jun 26, 2017
End Date Jun 29, 2017
Acceptance Date May 25, 2017
Online Publication Date Jun 26, 2017
Publication Date Dec 18, 2017
Deposit Date Sep 4, 2017
Publicly Available Date Sep 4, 2017
Print ISSN 1613-0073
Publisher CEUR Workshop Proceedings
Pages 85-94
Series Title CEUR workshop proceedings
Series Number 2028
Series ISSN 1613-0073
Keywords Case based reasoning; Siamese neural networks; Categorisation; SelfBACK
Public URL http://hdl.handle.net/10059/2490
Publisher URL http://ceur-ws.org/Vol-2028/paper8.pdf

Files







You might also like



Downloadable Citations