Learning from the Past Training Trajectories: Regularization by Validation.
Enzhi ZhangMohamed WahibRui ZhongMasaharu MunetomoPublished in: J. Adv. Comput. Intell. Intell. Informatics (2024)
Keyphrases
- learning algorithm
- online learning
- data sets
- learning systems
- supervised learning
- learning speed
- structured prediction
- learning process
- knowledge acquisition
- unsupervised learning
- learning machines
- deep architectures
- online training
- stochastic gradient descent
- minimum error rate
- past experience
- feedforward neural networks
- regularization parameter
- training process
- learning analytics
- learning tasks
- support vector machine
- mobile robot
- training set
- reinforcement learning