Abstract
We propose a new analysis technique for neural networks, Neurodynamical Agglomerative Analysis (NAA), an analysis pipeline designed to compare class representations within a given neural network model. The proposed pipeline results in a hierarchy of class relationships implied by the network representation, i.e. a semantic hierarchy analogous to a human-made ontological view of the relevant classes. We use networks pretrained on the ImageNet benchmark dataset to infer semantic hierarchies and show the similarity to human-made semantic hierarchies by comparing them with the WordNet ontology. Further, we show using MNIST training experiments that class relationships extracted using NAA appear to be invariant to random weight initializations, tending toward equivalent class relationships across network initializations in sufficiently parameterized networks.
Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) - GRK 2340.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bach, S., et al.: On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7), e0130140 (2015)
Raghu, M., et al.: SVCCA: singular vector canonical correlation analysis for deep learning dynamics and interpretability. In: Advances in Neural Information Processing Systems (2017)
Deng, L.: The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29(6), 141–142 (2012)
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2009)
Fellbaum, C.: WordNet. In: Poli, R., Healy, M., Kameas, A. (eds.) Theory and Applications of Ontology: Computer Applications, pp. 231–243. Springer, Dordrecht (2010). https://doi.org/10.1007/978-90-481-8847-5_10
Li, Y., et al.: Convergent learning: do different neural networks learn the same representations?. In: FE@ NIPS (2015)
Hardoon, D.R., Szedmak, S., Shawe-Taylor, J.: Canonical correlation analysis: an overview with application to learning methods. Neural Comput. 16(12), 2639–2664 (2004)
Jaeger, H.: Controlling recurrent neural networks by conceptors. arXiv preprint arXiv:1403.3369 (2014)
Müllner, D.: Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378 (2011)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12(Oct), 2825–2830 (2011)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
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
Marino, M., Schröter, G., Heidemann, G., Hertzberg, J. (2020). Hierarchical Modeling with Neurodynamical Agglomerative Analysis. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-030-61609-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61608-3
Online ISBN: 978-3-030-61609-0
eBook Packages: Computer ScienceComputer Science (R0)