Symbolic DNN-Tuner: A Python and ProbLog-based system for optimizing Deep Neural Networks hyperparameters.
Michele FraccaroliEvelina LammaFabrizio RiguzziPublished in: SoftwareX (2022)
Keyphrases
- hyperparameters
- neural network
- model selection
- bayesian inference
- cross validation
- closed form
- support vector
- em algorithm
- random sampling
- training process
- bayesian framework
- noise level
- gaussian process
- prior information
- sample size
- maximum likelihood
- incremental learning
- gaussian processes
- maximum a posteriori
- incomplete data
- artificial neural networks
- parameter estimation
- missing values
- parameter settings
- grid search
- approximate inference
- computer vision
- reinforcement learning
- expectation maximization
- decision trees
- data sets
- missing data
- back propagation
- genetic algorithm
- prior knowledge