Lifelong Machine Learning Architecture for Classification



Hong, Xianbin ORCID: 0000-0003-1678-0948, Guan, Sheng-Uei, Man, Ka Lok and Wong, Prudence WH ORCID: 0000-0001-7935-7245
(2020) Lifelong Machine Learning Architecture for Classification. SYMMETRY-BASEL, 12 (5). p. 852.

Access the full-text of this item by clicking on the Open Access link.

Abstract

<jats:p>Benefiting from the rapid development of big data and high-performance computing, more data is available and more tasks could be solved by machine learning now. Even so, it is still difficult to maximum the power of big data due to each dataset is isolated with others. Although open source datasets are available, algorithms’ performance is asymmetric with the data volume. Hence, the AI community wishes to raise a symmetric continuous learning architecture which can automatically learn and adapt to different tasks. Such a learning architecture also is commonly called as lifelong machine learning (LML). This learning paradigm could manage the learning process and accumulate meta-knowledge by itself during learning different tasks. The meta-knowledge is shared among all tasks symmetrically to help them to improve performance. With the growth of meta-knowledge, the performance of each task is expected to be better and better. In order to demonstrate the application of lifelong machine learning, this paper proposed a novel and symmetric lifelong learning approach for sentiment classification as an example to show how it adapts different domains and keeps efficiency meanwhile.</jats:p>

Item Type: Article
Uncontrolled Keywords: lifelong machine learning, continuous learning, sentiment classification, natural language processing
Depositing User: Symplectic Admin
Date Deposited: 01 Jun 2020 08:43
Last Modified: 15 Mar 2024 04:09
DOI: 10.3390/sym12050852
Open Access URL: https://www.mdpi.com/2073-8994/12/5/852
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3089251