On Neural Network Kernels and the Storage Capacity Problem.


Journal

Neural computation
ISSN: 1530-888X
Titre abrégé: Neural Comput
Pays: United States
ID NLM: 9426182

Informations de publication

Date de publication:
15 04 2022
Historique:
received: 14 11 2021
accepted: 13 01 2022
pubmed: 29 3 2022
medline: 27 4 2022
entrez: 28 3 2022
Statut: ppublish

Résumé

In this short note, we reify the connection between work on the storage capacity problem in wide two-layer treelike neural networks and the rapidly growing body of literature on kernel limits of wide neural networks. Concretely, we observe that the "effective order parameter" studied in the statistical mechanics literature is exactly equivalent to the infinite-width neural network gaussian process kernel. This correspondence connects the expressivity and trainability of wide two-layer neural networks.

Identifiants

pubmed: 35344992
pii: 110043
doi: 10.1162/neco_a_01494
doi:

Types de publication

Journal Article Research Support, Non-U.S. Gov't

Langues

eng

Sous-ensembles de citation

IM

Pagination

1136-1142

Informations de copyright

© 2022 Massachusetts Institute of Technology.

Auteurs

Jacob A Zavatone-Veth (JA)

Department of Physics and Center for Brain Science, Harvard University, Cambridge, MA 02138, U.S.A. jzavatoneveth@g.harvard.edu.

Cengiz Pehlevan (C)

Center for Brain Science and John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, U.S.A. cpehlevan@seas.harvard.edu.

Articles similaires

Selecting optimal software code descriptors-The case of Java.

Yegor Bugayenko, Zamira Kholmatova, Artem Kruglov et al.
1.00
Software Algorithms Programming Languages
1.00
Humans Magnetic Resonance Imaging Brain Infant, Newborn Infant, Premature
Humans Algorithms Software Artificial Intelligence Computer Simulation

Unsupervised learning for real-time and continuous gait phase detection.

Dollaporn Anopas, Yodchanan Wongsawat, Jetsada Arnin
1.00
Humans Gait Neural Networks, Computer Unsupervised Machine Learning Walking

Classifications MeSH