Abstract
Neural Networks are able to cluster data sets and our goal was to figure out how well the neural network clustered. The MNIST data set was ran through a neural network and the distances were extracted from both the feature and output layer. Five different distances were used on both layers. K-means clustering was used assess the clustering performance of each layer in the neural network. Results conveyed that the feature layer was not as proficient at clustering when compared to the output layer. The type of distance did not make a significant difference for clustering. These conclusions can be derived from qualitative observation of the cluster graphs. By observing the clustering performance of the different layers in the CNN, we are able to gain insight on the neural network.
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
Measuring distance or similarity. Packt Subscription
Likas, A., Vlassis, N., Verbeek, J.J.: The global k-means clustering algorithm. Pattern Recogn. 36(2), 451–461 (2003). https://doi.org/10.1016/S0031-3203(02)00060-2. http://www.sciencedirect.com/science/article/pii/S0031320302000602. Biometrics
Mao, J., Jain, A.K.: Artificial neural networks for feature extraction and multivariate data projection. IEEE Trans. Neural Netw. 6(2), 296–317 (1995)
Mao, Y., Yin, Z., Schober, J.: A deep convolutional neural network trained on representative samples for circulating tumor cell detection. In: 2016 IEEE Winter Conference, pp. 1–6. IEEE (2016)
Pradeep, J., Srinivasan, E., Himavathi, S.: Diagonal based feature extraction for handwritten character recognition system using neural network. In: 2011 3rd International Conference on Electronics, vol. 4, pp. 364–368. IEEE (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Schleider, L., Pasiliao, E.L., Zheng, Q.P. (2020). Graph-Based Supervised Clustering in Vector Space. In: Chellappan, S., Choo, KK.R., Phan, N. (eds) Computational Data and Social Networks. CSoNet 2020. Lecture Notes in Computer Science(), vol 12575. Springer, Cham. https://doi.org/10.1007/978-3-030-66046-8_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-66046-8_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66045-1
Online ISBN: 978-3-030-66046-8
eBook Packages: Computer ScienceComputer Science (R0)