| Proj No. | A3211-251 |
| Title | Part 2 of Deep Learning with Small Datasets: A Comparative Study |
| Summary | Deep learning typically requires large amounts of data to train effective models. However, in many practical scenarios, acquiring a large dataset is challenging due to constraints like limited resources, privacy concerns, or the rarity of the phenomena being studied. This project aims to explore techniques that enable deep learning to perform well on small datasets, addressing the challenges and proposing solutions to leverage the power of deep learning in data-scarce environments. The student should (1) carry out a literature survey on the topic, (2) gain hands-on experiences using either an existing program downloaded from the Internet or a new program coded by the student for an existing approach, and (3) then summerize and compare the advantages and disadvantages of different deep learning approaches to small datasets. This is part 2 of the project. The students in both parts will coordinate with the supervisor and each other so that each student will compare a different set of approaches. |
| Supervisor | A/P Wang Lipo (Loc:S1 > S1 B1C > S1 B1C 98, Ext: +65 67906372) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Computer Engineering I (Loc: S2-B4c-15) |
| Single/Group: | Single |
| Area: | Digital Media Processing and Computer Engineering |
| ISP/RI/SMP/SCP?: |