Knowledge-Driven Backdoor Removal in Deep Neural Networks via Reinforcement Learning.
Jiayin SongYike LiYunzhe TianXingyu WuQiong LiEndong TongWenjia NiuZhenguo ZhangJiqiang LiuPublished in: KSEM (3) (2024)
Keyphrases
- knowledge driven
- neural network
- reinforcement learning
- biomedical data
- query relaxation
- function approximators
- function approximation
- pattern recognition
- microarray
- learning capabilities
- markov decision processes
- artificial neural networks
- state space
- fuzzy logic
- back propagation
- optimal policy
- genetic algorithm
- learning algorithm
- databases
- reinforcement learning algorithms
- database systems
- temporal difference
- model free
- high throughput
- data mining