Abstract | ||
---|---|---|
Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are of prescribed size and can degenerate the performance for both learned tasks and coming ones when facing with a new task envi... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TNNLS.2020.3042500 | IEEE Transactions on Neural Networks and Learning Systems |
Keywords | DocType | Volume |
Task analysis,Libraries,Knowledge engineering,Learning systems,Neural networks,Computational modeling,Sun | Journal | 33 |
Issue | ISSN | Citations |
4 | 2162-237X | 1 |
PageRank | References | Authors |
0.35 | 16 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gan Sun | 1 | 64 | 13.55 |
Yang Cong | 2 | 684 | 38.22 |
Qianqian Wang | 3 | 132 | 26.59 |
Bineng Zhong | 4 | 1 | 0.69 |
Yun Fu | 5 | 4267 | 208.09 |