Duong Ngoc Yen

Duong Ngoc Yen (1)
Q: Share something about yourself.

My name is Duong Ngoc Yen. I am a Year-Two student at Nanyang Technological University (NTU), majoring in Computer Science. As I want to pursue a Ph.D. in the future, I started my 10-week internship with A*STAR’s Institute of High Performance Computing (IHPC) starting from end of May 2021 to explore research methods and learn more about the deep learning field. 

Q: Tell us about what you do at IHPC?

At IHPC, I had the opportunity to work under Dr Xu Xinxing, Scientist and Ng Yi Pin, Researcher Engineer, from the Computing & Intelligence Department who gave me plenty of valuable advice, comments and ideas.

I was involved in the project titled Multimodal learning for medical data analysis, covering two main topics on deep learning for tabular data and medical image segmentation. My focus was on the deep learning for tabular data, while another intern, Joshua Chan, worked on the latter. We would share our findings and our supervisors would give comments and advice at our weekly meetings.

I did literature review on the current deep learning models, i.e., TabNet, performed on tabular data, tested the reproducibility of the results from the published papers. After that, I fine-tuned and optimised the performance of the current machine learning models, such as random forest, MLPClassifier and CatBoost) on the provided medical datasets to see if the TabNet outperforms the current models. After testing, I tried to further improve the performance of the TabNet by modifying the model’s structure. 

I was pretty lost at the initial stage due to the complexity of the model structure. Hence I took multiple attempt to develop a new structure, including applying continuous features embedding steps, applying attention mechanism between datapoints in the tabular dataset, tabular data augmentation and self-supervised learning. Finally, together with my supervisors’ guidance, I managed to develop the new structure. Before each attempt, I would read up the relevant research papers, draft the ideas onto the architecture, implement, and then test the results. Some results showed better results than the others.

Q: What/Who is your inspiration in life?

My family is the biggest inspiration in my life. Despite living in a place where girls are usually encouraged to marry early, my parents nurtured me with education instead. My mother always tells me that she  is envious of me, being a young lady who is able to experience participating in a school competition or receiving education in a cohesive learning environment in a foreign country. I feel fortunate and am motivated to pursue my dreams whenever I think about my family back in my hometown. 

Duong Ngoc Yen (2)
My family trip to Po Nagar Cham Towers in Nha Trang, Vietnam

Q: Describe a typical work week.

Due to the COVID-19 situation,  my entire team worked from home. Usually, I would set a weekly goal by spending the first three days doing literature reviews and planning the following week’s presentation to showcase my work / new ideas. For the remaining days, I would try to implement and test out the models. However, there were some weeks when I spent more time drafting my ideas or testing models which could take up an entire week.  

Q: How has this internship benefits you?

This internship gave me an opportunity, a direction, a specific project to dive in deeply. I gained a lot more knowledge from reading research papers and hands-on experience. I am now more confident  to use my research skills to solve problems when I faced any problem. With the internship coming to an end, I discovered that I  have developed a deeper interest in computational research as I enjoyed the whole process. The weekly meetings also hone my presentation and communication skills that would be beneficial in my career path.