Unlocking the Full Potential of Neural NILM: On Automation, Hyperparameters, and Modular Pipelines.
Hafsa BousbiatAnthony FaustineChristoph KlemenjakLucas PereiraWilfried ElmenreichPublished in: IEEE Trans. Ind. Informatics (2023)
Keyphrases
- hyperparameters
- model selection
- closed form
- bayesian framework
- cross validation
- bayesian inference
- maximum a posteriori
- regularization parameter
- prior information
- neural network
- gaussian process
- support vector
- random sampling
- maximum likelihood
- sample size
- gaussian processes
- em algorithm
- multiscale
- incomplete data
- learning environment
- data mining
- sliding window
- parameter space
- wavelet transform
- high dimensional
- computer vision