Skip to main navigation
Skip to search
Skip to main content
Experts@Minnesota Home
!!Search content at Experts@Minnesota
Home
Profiles
Research units
University Assets
Projects and Grants
Research output
Datasets
Press/Media
Activities
Fellowships, Honors, and Prizes
Impacts
META-LEARNING PRIORS USING UNROLLED PROXIMAL NETWORKS
Yilang Zhang
,
Georgios B. Giannakis
Electrical and Computer Engineering
Research output
:
Contribution to conference
›
Paper
›
peer-review
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'META-LEARNING PRIORS USING UNROLLED PROXIMAL NETWORKS'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Meta-learning
100%
Learned Prior
100%
Performance Improvement
33%
Neural Network
33%
Nonsmooth
33%
Tight
33%
Approaches to Learning
33%
Probability Density Function
33%
Validation Data
33%
Numerical Test
33%
Expressiveness
33%
Recurrent Neural Network
33%
Proximal Gradient Method
33%
Empirical Performance
33%
Representation Model
33%
Piecewise Linear Function
33%
Proximal Operator
33%
Few-shot Learning
33%
Recent Approaches
33%
Limited Training Data
33%
Prior Representation
33%
Theoretical Error Bound
33%
Proximal Functions
33%
Algorithm Unrolling
33%
Computer Science
Meta-Learning
100%
Recurrent Neural Network
33%
Few-Shot Learning
33%
Interpretability
33%
Representation Model
33%
Proximal Gradient Descent
33%
piecewise linear
33%
Neural Network
33%
Training Data
33%
Probability Density Function
33%
Linear Function
33%
Neuroscience
Neural Network
100%
Recurrent Neural Network
100%
Few-Shot Learning
100%
Earth and Planetary Sciences
Probability Density Function
100%
Interpretability
100%