RPR-BP: A Deep Reinforcement Learning Method for Automatic Hyperparameter Optimization.
Jia WuSenpeng ChenXiuyun ChenPublished in: IJCNN (2019)
Keyphrases
- significant improvement
- reinforcement learning
- fully automatic
- dynamic programming
- optimization model
- optimization method
- high accuracy
- probabilistic model
- artificial neural networks
- edge detection
- model selection
- optimization algorithm
- clustering method
- pairwise
- preprocessing
- computational cost
- cost function
- support vector machine
- cross validation
- function approximation
- bayesian inference
- feature selection