Goal-Oriented Sensitivity Analysis of Hyperparameters in Deep Learning.
Paul NovelloGaël PoëtteDavid LugatoPietro Marco CongedoPublished in: CoRR (2022)
Keyphrases
- sensitivity analysis
- deep learning
- goal oriented
- hyperparameters
- model selection
- cross validation
- bayesian inference
- closed form
- support vector
- prior information
- bayesian framework
- random sampling
- unsupervised learning
- noise level
- em algorithm
- maximum likelihood
- managerial insights
- sample size
- gaussian process
- incremental learning
- maximum a posteriori
- machine learning
- variational inequalities
- incomplete data
- prior knowledge
- probabilistic model
- missing values
- pattern recognition
- active learning
- expectation maximization
- weakly supervised
- mental models
- pairwise
- higher order
- graphical models
- noisy images
- text classification
- image segmentation
- data mining