Rhea Iyer
Major: Computer Science
Research Department: Radiation Oncology
Graduation Date: May 2022
Email: rxi180001@utdallas.edu
Abstract: Conventional deep learning algorithms have been traditionally designed to work in isolation and are only used to solve specific tasks. Transfer learning is the idea of reusing knowledge gained from a previous task and applying it to a new one. This machine learning technique aims to yield better performance and reduce training time and computing resources by a significant amount as compared to retraining a model from scratch. My research aims to prove the increased efficiency of transfer learning by using its techniques on a convolutional neural network model that is pre-trained to identify COVID-19 positive patients has a better overall accuracy and requires significantly less data than using the isolated methods of updating and training the model from scratch.
​What does research mean to you?
To me, research is a space for unlimited growth and learning. It allows creativity and innovation to mesh together to help deepen our understanding of the world around us and shows how even the smallest of steps help in answering bigger questions that impact our society.
​
Tell us about your journey.
I was always unsure about what I wanted to pursue as my career, but the one thing that I knew for certain was that I loved learning. My first venture into research was in an Electrical Engineering lab at UTD, where I was thrown into a whole new world of hardware, recurrent neural networks, and machines. Although daunting at first, I loved immersing myself into a whole new field and started looking at computer science with a different perspective. When I heard of the green fellowship program, I was hesitant to apply at first as it seemed more catered towards students pursuing health and medical sciences and as a computer science major, I didn’t know if I would have a place in the program. As I explored the different labs and their research, I found that technology really does have a place everywhere and decided that this would be a phenomenal opportunity for me to learn about how my technical skills apply to yet another field. I have learned a lot through the duration of this program, and I have a whole lot more of learning to do. This program has further solidified my belief that my love for learning and a career in research go hand in hand.
What was your favorite part of the program?
My favorite part of the program was meeting some truly wonderful people! My mentors in lab were wonderful to work with and were very patient with my endless questions. It was so nice to meet the other Green Fellows and learn about their work and passions, and of course, the amazing coordinators of the program who are always so kind and inspiring.
What was the biggest thing you learned from the program?
The biggest thing I learned was to be confident in myself. At the beginning, I was scared of asking questions because I didn’t want to seem inferior and thought my questions were unintelligent. Throughout the course of the program, I learned that if I didn’t ask, I wouldn’t learn. I learned how to prioritize gaining knowledge and started worrying less about my lack of experience. After all, everyone has a beginning.
​
Advice for Future Green Fellows
​Be confident and ask questions! It may seem intimidating at first as you will be working with people who are experts in the field, but everyone has your best interests at heart and only want you to succeed. Allow yourself to make mistakes and work with an open mind. If you feel lost in the beginning, know that you’re doing something right. :)