Training-Free Neural Active Learning with Initialization-Robustness Guarantees.
Apivich HemachandraZhongxiang DaiJasraj SinghSee-Kiong NgBryan Kian Hsiang LowPublished in: CoRR (2023)
Keyphrases
- active learning
- training examples
- training set
- supervised learning
- annotation effort
- neural network
- recurrent networks
- training phase
- network architecture
- selective sampling
- training process
- imbalanced data classification
- data sets
- sample selection
- batch mode
- test set
- training samples
- feed forward neural networks
- online learning
- semi supervised
- learning algorithm
- random sampling
- sample size
- learning strategies
- bio inspired
- initial state
- reinforcement learning
- decision trees