Abstract
In the field of artificial intelligence, agents learn how to take decisions by fitting their parameters on a set of samples called training set. Similarly, a core set is a subset of the training samples such that, if an agent exploits this set to fit its parameters instead of the whole training set, then the quality of the inferences does not change significantly. Relaxing the constraint that restricts the search for core sets to the available data, neural networks may be used to generate virtual samples, called archetype set, containing the same kind of information. This work illustrates the features of GH-ARCH, a recently proposed self-organizing hierarchical neural network for archetype discovery. Experiments show how the use of archetypes allows both ML agents to make fast and accurate predictions and human experts to make sense of such decisions by analyzing few important samples.
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
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)
Mitchell Waldrop, M.: News feature: what are the limits of deep learning? Proc. Natl. Acad. Sci. 116(4), 1074–1077 (2019)
Bachem, O., Lucic, M., Krause, A.: Practical coreset constructions for machine learning. arXiv preprint arXiv:1703.06476 (2017)
Ciravegna, G., Barbiero, P., Cirrincione, G., Squillero, G., Tonda, A.: Discovering hierarchical neural archetype sets. In: The International Joint Conference on Neural Networks (IJCNN), July 2019
Cirrincione, G., Ciravegna, G., Barbiero, P., Randazzo, V., Pasero, E.: The GH-EXIN neural network for hierarchical clustering. Neural Networks (2019, under peer review)
Haykin, S.S.: Neural Networks and Learning Machines, vol. 3. Pearson, Upper Saddle River (2009)
Cirrincione, G., Randazzo, V., Pasero, E.: The growing curvilinear component analysis (GCCA) neural network. Neural Netw. 103, 108–117 (2018)
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Tikhonov, A.N.: On the stability of inverse problems. Dokl. Akad. Nauk SSSR 39, 195–198 (1943)
Vanschoren, J., van Rijn, J.N., Bischl, B., Torgo, L.: OpenML: networked science in machine learning. SIGKDD Explorations 15(2), 49–60 (2013)
Breiman, L.: Pasting small votes for classification in large databases and on-line. Mach. Learn. 36(1–2), 85–103 (1999)
Cox, D.R.: The regression analysis of binary sequences. J. Roy. Stat. Soc.: Ser. B (Methodol.) 20, 215–242 (1958)
Campbell, T., Broderick, T.: Bayesian coreset construction via greedy iterative geodesic ascent. In: International Conference on Machine Learning (ICML) (2018)
Clarkson, K.L.: Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm. ACM Trans. Algorithms 6, 63 (2010)
Pati, Y.C., Rezaiifar, R., Krishnaprasad, P.S.: Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition. In: Proceedings of 27th Asilomar Conference on Signals, Systems and Computers, pp. 40–44 (1993)
Efron, B., Hastie, T., Johnstone, I., Tibshirani, R.: Least angle regression. Ann. Stat. 32(2), 407–451 (2004)
Boutsidis, C., Drineas, P., Magdon-Ismail, M.: Near-optimal coresets for least-squares regression. Technical report (2013)
Efroymson, M.A.: Multiple regression analysis. Math. Methods Digital Comput. (1960)
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
Barbiero, P., Ciravegna, G., Cirrincione, G., Tonda, A., Squillero, G. (2020). Generating Neural Archetypes to Instruct Fast and Interpretable Decisions. In: Bucciarelli, E., Chen, SH., Corchado, J. (eds) Decision Economics: Complexity of Decisions and Decisions for Complexity. DECON 2019. Advances in Intelligent Systems and Computing, vol 1009. Springer, Cham. https://doi.org/10.1007/978-3-030-38227-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-38227-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-38226-1
Online ISBN: 978-3-030-38227-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)