Learning Automata Based Incremental Learning Method for Deep Neural Networks
Deep learning methods have got fantastic performance on lots of large-scale datasets for machine learning tasks, such as visual recognition and neural language processing. Most of the progress on deep learning in recent years lied on supervised learning, for which the whole dataset with respect to a...
Main Authors: | Haonan Guo, Shilin Wang, Jianxun Fan, Shenghong Li |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2019-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8674746/ |
Similar Items
-
Reduce the Difficulty of Incremental Learning With Self-Supervised Learning
by: Linting Guan, et al.
Published: (2021-01-01) -
Extracting automata from neural networks using active learning
by: Zhiwu Xu, et al.
Published: (2021-04-01) -
Consumption Behavior Analysis of Over the Top Services: Incremental Learning or Traditional Methods?
by: Juan Sebastian Rojas, et al.
Published: (2019-01-01) -
Class Incremental Learning With Large Domain Shift
by: Kamin Lee, et al.
Published: (2024-01-01) -
Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
by: Syed Shakib Sarwar, et al.
Published: (2020-01-01)