Skip to main navigation
Skip to search
Skip to main content
Experts@Minnesota Home
Home
Profiles
Research units
University Assets
Projects and Grants
Research output
Datasets
Press/Media
Activities
Fellowships, Honors, and Prizes
Search by expertise, name or affiliation
Understanding Double Descent Using VC-Theoretical Framework
Eng Hock Lee,
Vladimir Cherkassky
Electrical and Computer Engineering
Research output
:
Contribution to journal
›
Article
›
peer-review
3
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Understanding Double Descent Using VC-Theoretical Framework'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Double Descent
100%
Deep Learning Network
50%
Least Squares
25%
Support Vector Machine
25%
Training Data
25%
Overfitting
25%
Generalization Performance
25%
Model Complexity
25%
Underfitting
25%
Generalization Ability
25%
Deep Learning Applications
25%
Multilayer Perceptron Classifier
25%
Theoretical Understanding
25%
Learning Methods
25%
Bias-variance Tradeoff
25%
Overparameterized Network
25%
Computer Science
Theoretical Framework
100%
Deep Learning Method
100%
Model Complexity
50%
Generalization Performance
50%
least square support vector machine
50%
Training Data
50%
Multilayer Perceptron
50%
Mathematics
Deep Learning Method
100%
Variance
50%
Optimal Model
50%
Training Data
50%
Multilayer Perceptron
50%
least square support vector machine
50%
Earth and Planetary Sciences
Self Organizing Systems
100%
Support Vector Machine
100%
Medicine and Dentistry
Least Squares Method
100%