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
A New Likelihood Ratio Method for Training Artificial Neural Networks
Yijie Peng
, Li Xiao
, Bernd Heidergott
,
L. Jeff Hong
, Henry Lam
Research output
:
Contribution to journal
›
Article
›
peer-review
12
Link opens in a new tab
Scopus citations
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'A New Likelihood Ratio Method for Training Artificial Neural Networks'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Artificial Neural Network
100%
Likelihood Ratio
100%
Backpropagation
37%
Back Propagation Algorithm
37%
Stochastic Gradient Estimation
37%
Loss Function
25%
Activation Function
25%
Gradient Estimation
25%
Popular
25%
Infinitesimal Perturbation Analysis
25%
Machine Learning
12%
Simulation Training
12%
Artificial Intelligence
12%
Deep Learning
12%
Computational Complexity
12%
Estimation Approaches
12%
Ratio-based
12%
Stochastic Gradient Descent
12%
Natural Noise
12%
Adversarial Attack
12%
Adversarial Corruptions
12%
Derivative Estimation
12%
Efficient Training
12%
Neural Network-based
12%
Artificial Noise
12%
Network Perturbation
12%
Backward Recursion
12%
New Training Method
12%
Mathematics
Ratio Method
100%
Likelihood Ratio
100%
Neural Network
100%
Stochastics
50%
Loss Function
12%
Estimation Approach
12%
Deep Learning Method
12%
Adversarial Attack
12%
Computer Science
Neural Network
100%
Likelihood Ratio
100%
Perturbation Analysis
25%
Activation Function
25%
Computational Complexity
12%
Adversarial Machine Learning
12%
Machine Learning
12%
Learning System
12%
Deep Learning Method
12%
Artificial Intelligence
12%
Stochastic Gradient Descent
12%