Learning curves for overparametrized deep neural networks: A field theory perspective
In the past decade, deep neural networks (DNNs) came to the fore as the leading machine-learning algorithms for a variety of tasks. Their rise was founded on market needs and engineering craftsmanship, the latter based more on trial and error than on theory. While still far behind the application fo...
Main Authors: | Omry Cohen, Or Malka, Zohar Ringel |
---|---|
Format: | Article |
Language: | English |
Published: |
American Physical Society
2021-04-01
|
Series: | Physical Review Research |
Online Access: | http://doi.org/10.1103/PhysRevResearch.3.023034 |
Similar Items
-
Effects of noise on the overparametrization of quantum neural networks
by: Diego García-Martín, et al.
Published: (2024-03-01) -
Topics in Sparsity and Compression: From High dimensional
statistics to Overparametrized Neural Networks
by: Benbaki, Riade
Published: (2023) -
Intrinsic sign problems in topological quantum field theories
by: Adam Smith, et al.
Published: (2020-09-01) -
A mean field theory learning algorithm for neural networks /
by: 323731 Peterson, Carsten, et al. -
Separation of scales and a thermodynamic description of feature learning in some CNNs
by: Inbar Seroussi, et al.
Published: (2023-02-01)