Skip to main navigation
Skip to search
Skip to main content
Korea University Pure Home
Home
Profiles
Research units
Equipment
Research output
Press/Media
Search by expertise, name or affiliation
Learning to Balance Local Losses via Meta-Learning
Seungdong Yoa
, Minkyu Jeon
, Youngjin Oh
, Hyunwoo J. Kim
*
*
Corresponding author for this work
Research output
:
Contribution to journal
›
Article
›
peer-review
1
Citation (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Learning to Balance Local Losses via Meta-Learning'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Loss Function
100%
Meta-learning
100%
Local Loss
100%
Deep Neural Network
50%
State-of-the-art Techniques
25%
Popular
25%
Benchmark Dataset
25%
Overfitting
25%
Local Error
25%
Competitive Performance
25%
Error Signal
25%
Image Classification
25%
Dropout
25%
Effective Training
25%
CIFAR-10
25%
Global Loss
25%
Skip Connection
25%
CIFAR-100
25%
Training Deep Neural Networks
25%
Complex Deep Neural Networks
25%
Training Dynamics
25%
Dynamic Loss Function
25%
Computer Science
Deep Neural Network
100%
Meta-Learning
100%
Image Classification
25%