Swapping training optimizers and tiny partial datasets to improve performance of lighter neural networks for edge devices.
Alexandre Moreira NascimentoVinícius Veloso de MeloMárcio P. BasgaluppPublished in: SAC (2023)
Keyphrases
- neural network
- training process
- pattern recognition
- genetic algorithm
- neural network training
- test set
- training algorithm
- training dataset
- mobile devices
- supervised learning
- training phase
- multi layer perceptron
- image processing
- artificial neural networks
- control system
- fuzzy logic
- edge detection
- benchmark datasets
- neural network model
- training set
- information loss