Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets.
Yan HongLi NiuJianfu ZhangLiqing ZhangPublished in: CoRR (2020)
Keyphrases
- multi task learning
- binary classification tasks
- multi task
- gaussian processes
- incremental learning
- multi label image annotation
- decision trees
- learning problems
- multiple tasks
- multi class
- learning tasks
- feature vectors
- machine learning algorithms
- theoretical analysis
- machine learning
- supervised learning
- training set
- unsupervised learning
- image classification
- classification accuracy
- support vector
- random walk
- high order
- learning process
- training data
- feature extraction
- data sets