Abstract
Recently, the applications of Artificial Intelligence are widely spread in many areas of research. They almost use tailor made classification engine of Deep Learning, and many of such engines uses Convolutional Neural Networks. In this paper, we propose a method for preprocessing the un-structured data to the 2 dimensional data suitable for CNN using Self Organizing Map. The performance is evaluated with the experiments using KDD cup 99 data as input vectors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Caglar Gulcehre Deep Learning. http://deeplearning.net
FLDL Tutrial: Convolutional Neural Network. http://ufldl.stanford.edu/tutral/supervised/Convolutiona/Neural
Otani, G., Takase, H., Kobayashi, R., Kato, M.: Detection of Subspecific Malware Focusing on Processor Level Features, IPSJ-CSEC18080031 (2018)
Kohonen, T.: Self Organizing Maps. Springer, Heidelberg (2001). https://doi.org/10.1007/978-3-642-56927-2. ISBN 3-540-67921-9
KDD Cup 1999 Data. http://kdd.ics.uci.edu/databases/kddcup99/kddcup99.html
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Dozono, H., Tanaka, M. (2019). Application of Self Organizing Map to Preprocessing Input Vectors for Convolutional Neural Network. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Deep Learning. ICANN 2019. Lecture Notes in Computer Science(), vol 11728. Springer, Cham. https://doi.org/10.1007/978-3-030-30484-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-30484-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30483-6
Online ISBN: 978-3-030-30484-3
eBook Packages: Computer ScienceComputer Science (R0)