2018
DOI: 10.48550/arxiv.1811.06100
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Newton Methods for Convolutional Neural Networks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2019
2019
2019
2019

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 0 publications
0
1
0
Order By: Relevance
“…solving with the Hessian matrix in a Newton method. As a result the applicability of Newton-type schemes for the computation of W (j) and b (j) has received more attention with a strong focus on exploiting the structure of the Hessian matrix [32,61,275,47,227,271]. The computational complexity of neural networks is challenging on many levels.…”
Section: Functions Of Matrices the Concept Of Evaluating A Function O...mentioning
confidence: 99%
“…solving with the Hessian matrix in a Newton method. As a result the applicability of Newton-type schemes for the computation of W (j) and b (j) has received more attention with a strong focus on exploiting the structure of the Hessian matrix [32,61,275,47,227,271]. The computational complexity of neural networks is challenging on many levels.…”
Section: Functions Of Matrices the Concept Of Evaluating A Function O...mentioning
confidence: 99%