A Design of Continuous Learning System Based on Knowledge Augmentation
| Autor: | Hyun-Jae Kim, Soon Hyun Kwon, Nae-Soo Kim, Ho Sung Lee, Kwihoon Kim, Eun Joo Kim, Hyunjoong Kang |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer science
Active learning (machine learning) business.industry Multi-task learning Online machine learning 02 engineering and technology Semi-supervised learning Machine learning computer.software_genre Robot learning Inductive transfer 020204 information systems 0202 electrical engineering electronic engineering information engineering Unsupervised learning 020201 artificial intelligence & image processing Instance-based learning Artificial intelligence business computer |
| Zdroj: | 2017 International Conference on Platform Technology and Service (PlatCon). |
| DOI: | 10.1109/platcon.2017.7883675 |
| Popis: | To create an algorithm with Machine Learning, users should understand all the knowledge such as learning rate, activation, dimension reduction, hyper parameter, neural network, etc. Therefore, in order to construct a machine learning procedure, expert knowledge is required. So, it is difficult for general users to use it. Also, experts are also hard to regenerate well-defined model if it is described only in the paper. In this paper, we propose a knowledge based Continuous Learning System (CLS) which persistently collect and infer new knowledge from information for the existing learning setup and results instantiated based on a hierarchically designed ontology model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|