Mixup Gamblers: Learning to Abstain with Auto-Calibrated Reward for Mixed Samples.

Takumi Yamaguchi Masahiro Murakawa

Published in: ICANN (2) (2021)

Keyphrases

reinforcement learning
data sets
learning algorithm
active learning
real time
unsupervised learning
learning tasks
neural network
genetic algorithm
learning process
supervised learning
expert systems
learning systems
background knowledge
learning scheme