Abstract
Dropout has been introduced as a simple yet effective method to prevent over-learning in deep learning. Although its mechanism, i.e., incapable of utilizing all memorized units, seems quite natural to human cognition, the effect of dropout on models of human cognition has not been addressed. In the present research, we apply dropout to a computational model of human category learning. We compared models with and without complete memorization abilities, and results showed that they differed acquired association weights, dimensional attention strengths, and how they handled exceptional exemplars.
Supported by JSPS KAKENHI JP16H02835.
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
Murphy, G.L.: The Big Book of Concepts. MIT Press, Cambridge (2002)
Medin, D.L., Ross, B.H., Markman, A.B.: Cognitive Psychology, 4th edn. Wiley, Hoboken (2005)
Kruschke, J.E.: ALCOVE: an exemplar-based connectionist model of category learning. Psychol. Rev. 99, 22–44 (1992)
Matsuka, T., Sakamoto, Y., Chouchourelou, A., Nickerson, J.V.: Toward a descriptive cognitive model of human learning. Neurocomputing 71(13–15), 2446–2455 (2008)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Ashby, F.G., Alfonso-Reese, L.A., Turken, A.U., Waldron, E.M.: A neuropsychological theory of multiple systems in category learning. Psychol. Rev. 3, 442–481 (1998)
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
Matsuka, T., Kawabbatas, Y., Xu, K. (2019). Effect of Incomplete Memorization in a Computational Model of Human Cognition. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)