Hostname: page-component-89b8bd64d-5bvrz Total loading time: 0 Render date: 2026-05-10T12:58:43.400Z Has data issue: false hasContentIssue false
  • English
  • Français

Explananda and explanantia in deep neural network models of neurological network functions

Published online by Cambridge University Press:  06 December 2023

Mihnea Moldoveanu Open the ORCID record for Mihnea Moldoveanu [Opens in a new window]
Mihnea Moldoveanu*
Affiliation:
Desautels Centre for Integrative Thinking, Rotman School of Management, University of Toronto, Toronto, ON, Canada mihnea.moldoveanu@rotman.utoronto.ca https://www.rotman.utoronto.ca/FacultyAndResearch/Faculty/FacultyBios/Moldoveanu
Get access Rights & Permissions [Opens in a new window]

Abstract

Depending on what we mean by “explanation,” challenges to the explanatory depth and reach of deep neural network models of visual and other forms of intelligent behavior may need revisions to both the elementary building blocks of neural nets (the explananda) and to the ways in which experimental environments and training protocols are engineered (the explanantia). The two paths assume and imply sharply different conceptions of how an explanation explains and of the explanatory function of models.

Information

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 46 , 2023 , e403
Check for updates
Copyright
Copyright © The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Balcazar, J. C., Gavalda, R., & Siegelmann, H. T. (1997). Computational power of neural networks: A characterization in terms of Kolmogorov complexity. IEEE Transactions on Information Theory, 43, 1175–1183.CrossRefGoogle Scholar
Beniaguev, D., Segev, I., & London, M. (2021) Single cortical neurons as deep artificial neural networks. Neuron, 109, 2727–2739.CrossRefGoogle ScholarPubMed
Hasani, R., Lechner, M., Amini, A., Rus, D., & Grosu, R. (2020). Liquid time constant networks. arXiv:2006.04439v4.Google Scholar
Jia, G., Lam, H.-K., & Althoefer, K. (2022). Variable weight algorithm for convolutional neural networks and its applications to classification of seizure phases and types. Pattern Recognition, 121, 108226.CrossRefGoogle Scholar
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., … Lowe, R. (2022). Training language models to follow instructions with human feedback. arXiv: 2203.02155v1.Google Scholar