| Proj No. | A3062-251 |
| Title | Class-incremental Learning by Time Series Foundation Model |
| Summary | Learning novel classes in a non-stationary environment presents a significant challenge for deep neural networks, particularly within the realm of time series data. This challenge defines the research area of Time Series Class-Incremental Learning (TSCIL). Despite extensive research on Class-Incremental Learning (CIL) in the image domain, TSCIL remains relatively unexplored, especially in terms of the utilization of large pre-trained models. Recently, several time series foundation models have been developed, extracting increased attention within the research community. The recent advent of the Time Series Foundation Model offers a promising solution to bridge this gap. This project aims to develop novel algorithms that leverage the Time Series Foundation Model to address the challenges of TSCIL effectively. |
| Supervisor | A/P Jiang Xudong (Loc:S1 > S1 B1C > S1 B1C 105, Ext: +65 67905018) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Centre for Information Sciences & System (CISS) (Loc: S2-B4b-05) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |