Abstract
For the neural network model where Pulse-in Pattern-out Network (PPN) is integrated into the autoencoder, we investigate how its information aggregation performance is affected by the number of epochs before switching the input layer between the PPN part and the autoencoder part in the training process. It is shown that the PPN-integrated network exhibits better information aggregation performance for lower dimensional training data in the case we switch the input parts less frequently by the longer interval of epochs. It is also shown that the PPN-integrated network works better for higher dimensional training data in the case we switch the input parts frequently by the shorter interval of epochs.
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
Similar content being viewed by others
References
Yonekura, T., Miyazaki, S., Toriwaki, J.: Analysis of the data integration function of the four layer neural network based on the auto association model and PPN. IEICE Trans. J74-D2(10), 1398–1410 (1991)
Okui, Y., Yonekura, T., Kamada, M.: Integrating PPN into autoencoders for better information aggregation performance. In: Barolli, L., Chen, H.-C., Enokido, T. (eds.) NBiS 2021. LNNS, vol. 313, pp. 359–366. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-84913-9_36
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313, 504–507 (2006)
Optical Recognition of Handwritten Digits Data Set. https://archive.ics.uci.edu/ml/datasets/optical+recognition+of+handwritten+digits. Accessed 2 May 2022
THE MNIST DATABASE of handwritten digits. http://yann.lecun.com/exdb/mnist/. Accessed 2 May 2022
The CIFAR-100 dataset. https://www.cs.toronto.edu/~kriz/cifar.html. Accessed 2 May 2022
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Okui, Y., Yonekura, T., Kamada, M. (2022). Evaluation of Information Aggregation Performance of PPN-Integrated Networks by Changing the Interval for Input Part Switching. In: Barolli, L., Miwa, H., Enokido, T. (eds) Advances in Network-Based Information Systems. NBiS 2022. Lecture Notes in Networks and Systems, vol 526. Springer, Cham. https://doi.org/10.1007/978-3-031-14314-4_47
Download citation
DOI: https://doi.org/10.1007/978-3-031-14314-4_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-14313-7
Online ISBN: 978-3-031-14314-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)