Bayesian Generalization Error in Linear Neural Networks with Concept Bottleneck Structure and Multitask Formulation.
Naoki HayashiYoshihide SawadaPublished in: CoRR (2023)
Keyphrases
- generalization error
- multi task
- neural network
- learning algorithm
- multi task learning
- multitask learning
- upper bound
- model selection
- maximum margin
- artificial neural networks
- sample size
- cross validation
- supervised learning
- data sets
- learning tasks
- active learning
- training set
- training error
- learning problems
- information gain
- multi class
- classification accuracy
- gaussian processes
- training data