2018 · 15 citations · 34 references
ComputingComputer ScienceArtificial IntelligenceComputer VisionMachine LearningChange DetectionChange-point DetectionDeep LearningPolicy LearningReinforcement LearningDeep Learning-based Change DetectionDeep Learning-based Change-point DetectionDeep Reinforcement LearningOne-shot LearningOnline Change-point DetectionQ-learning
We consider the problem of detecting a change in a time series quickly and reliably, where only a few training instances are available. Examples include identifying changes in network traffic due to zero-day attacks, and computer vision applications where changes in series of images that represent significant events needed to be detected. These are known as cases of one-shot learning. We develop a novel Deep Reinforcement One-shot Learning (DeROL) framework to address this challenge. The basic idea of the DeROL algorithm is to train a deep-Q network to obtain a policy which is oblivious to the unseen classes in the testing data. Then, in real-time, DeROL maps the current state of the one-shot learning process to operational actions based on the trained deep-Q network, to maximize the objective function. We tested the algorithm using the OMNIGLOT dataset to demonstrate the efficiency of the DeROL framework.
34
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations
Deep Reinforcement Learning with Double Q-Learning
Hado van Hasselt, Arthur Guez, David Silver · 2016 · 6K citations · Full text
Active Learning Literature Survey
Burr Settles · Minds at UW (University of Wisconsin) · 2009 · 4.8K citations · Full text