Parsimonious Inference on Convolutional Neural Networks: Learning and applying on-line kernel activation rules.
Ilias TheodorakopoulosVasileios K. PothosDimitris KastaniotisNikos FragoulisPublished in: CoRR (2017)
Keyphrases
- convolutional neural networks
- learning algorithm
- learning process
- prior knowledge
- component analysis
- learning systems
- inference process
- active learning
- online learning
- convolutional network
- efficient learning
- knowledge acquisition
- supervised learning
- object detection
- probabilistic model
- information processing
- learning environment
- learning problems
- human experts
- probabilistic inference
- bayesian inference
- inference engine
- reinforcement learning
- face recognition
- feature selection
- machine learning
- data mining