Hostname: page-component-7c8c6479df-94d59 Total loading time: 0 Render date: 2024-03-28T20:49:51.024Z Has data issue: false hasContentIssue false

Understand the cogs to understand cognition

Published online by Cambridge University Press:  10 November 2017

Adam H. Marblestone
Affiliation:
Synthetic Neurobiology Group, MIT Media Lab, Cambridge, MA 02474. adam.h.marblestone@gmail.comhttp://www.adammarblestone.org/
Greg Wayne
Affiliation:
DeepMind, London N1 9DR, UK. gregwayne@gmail.com
Konrad P. Kording
Affiliation:
Departments of Bioengineering and Neuroscience, University of Pennsylvania, Philadelphia, PA 19104. kording@upenn.eduwww.kordinglab.com

Abstract

Lake et al. suggest that current AI systems lack the inductive biases that enable human learning. However, Lake et al.'s proposed biases may not directly map onto mechanisms in the developing brain. A convergence of fields may soon create a correspondence between biological neural circuits and optimization in structured architectures, allowing us to systematically dissect how brains learn.

Type
Open Peer Commentary
Copyright
Copyright © Cambridge University Press 2017 

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.)

References

Blumberg, M. S. (2005) Basic instinct: The genesis of behavior. Basic Books.Google Scholar
Guergiuev, J., Lillicrap, T. P. & Richards, B. A. (2016) Toward deep learning with segregated dendrites. arXiv preprint 1610.00161. Available at: http://arxiv.org/pdf/1610.00161.pdf.Google Scholar
Ho, Y-C. & Pepyne, D. L. (2002) Simple explanation of the no-free-lunch theorem and its implications. Journal of Optimization Theory and Applications 115:549–70.CrossRefGoogle Scholar
Marblestone, A. H., Wayne, G. & Kording, K. P. (2016) Toward an integration of deep learning and neuroscience. Frontiers in Computational Neuroscience 10:94.CrossRefGoogle ScholarPubMed