Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs.
Yi SunXin XuJian LiXiaochang HuYifei ShiLing-Li ZengPublished in: CoRR (2023)
Keyphrases
- learning systems
- learning process
- learning algorithm
- reinforcement learning
- learning tasks
- prior knowledge
- active learning
- markov logic
- edge detection
- knowledge acquisition
- boltzmann machine
- inference process
- elementary school
- inductive inference
- learning analytics
- inductive logic programming
- probabilistic model
- case study