The Machine Learning Center at Georgia Tech (ML@GT) is home to many talented students from across campus, representing all six of Georgia Tech’s colleges and the Georgia Tech Research Institute (GTRI).
These students have diverse backgrounds and a wide variety of interests both inside and outside of the classroom. Today, we’d like you to meet Harsh Shrivastava, a fourth-year machine learning Ph.D. student. Originally from Nagpur, India, Shrivastava’s work could lead to a greater understanding of gene networks and help discover new and more effective drugs.
Advisor: Srinivas Aluru
Hometown: Nagpur, India
Current Georgia Tech degree program/year: Fourth-year machine learning Ph.D. student
Other degrees earned and from what institution: Dual Degree (B.Tech (Hon.) + M.Tech) in Electronics & ECE with specialization in VLSI circuit designing from Indian Institute of Technology Kharagpur
Tell us about your research interests.
My current research is on combining deep learning techniques with probabilistic graphical models for solving real-world problems. We usually end up with a highly structured deep neural network architecture specifically designed for the problem at hand.
We are currently investigating the application of our models to solving problems related to single-cell RNA sequencing and protein 3D structure prediction. Solving these problems will enhance our understanding of gene networks, help in drug discovery, etc. Though it takes a considerable amount of time and effort to gain a deep understanding of the complex nature of these problems, we are hopeful that our research can help improve the existing methods.
What is it about machine learning that excites you?
I view the field of machine learning as a graceful amalgamation of statistics, computer science & mathematics concepts. Furthermore, we can use these techniques to approach problems arising in quite diverse domains (finance, bioinformatics, etc.). I find such cross-domain research very interesting and given the fast pace at which ML-related research is moving, it excites me to think about the upcoming technological advancements!
What are some of your hobbies?
I enjoy playing racquet sports in general (squash, badminton, table tennis, etc.). Sometimes I read ancient philosophy literature on my Kindle.
We just entered a new decade. What are you most looking forward to in the next 10 years?
Tough question. I don’t know… maybe a startup of my own 🙂
Why did you choose Georgia Tech as the place to earn your Ph.D.?
It is one of the top schools. I consider myself lucky to be here.
What inspired or motivated you to earn a Ph.D. in machine learning?
In my undergrad days, I participated in quite a few CS/ML-based competitions. For instance, predicting the winning team for the upcoming Cricket World Cup, stock predictions for high-frequency trading, etc.
After completing my degree in 2014, I worked on healthcare-related problems for two years in a research lab. ML techniques were widely used there as well. I like the broad range of problems that can be tackled by ML. I consider myself very fortunate to have interacted with some of the top researchers in this field who helped me better understand CS & ML concepts and encouraged me to do a Ph.D. So, here I am!
What do you hope to do after graduation?
I’m hoping to do more research, travel, learn to play more music and hopefully get better at cooking.
What is your proudest accomplishment?
Getting those tricky backhand shots right in badminton. A close second is learning to play the F chord on the guitar.
Who is someone that inspires you and why?
As a kid, I was a big fan of this Japanese manga series called Doraemon. In the anime show, there is a futuristic robotic cat named Doraemon and he comes up with awesome gadget ideas to help his lazy school friend. If you are ever in search of new innovative ideas, I suggest give Doraemon a chance!
Podcast, movie, book, or tv show? Why is that your favorite medium and what is your favorite of your chosen medium?
I do watch a lot of movies. I feel that movies provide a good temporary distraction from work. Movies also help you gain different perspectives and, who knows, maybe some of that will help me with my research. It is not possible for me to choose a favorite movie!
Besides movies, I am a big fan of the books by Haruki Murakami, Khaled Hosseini & Munshi Premchand. I also happen to co-develop a short-stories podcast app named “Saraz”. We handpick short & interesting content for the app. Do try it out!
If you could dis-invent one thing what would it be and why?
Pineapple on pizza. I don’t think this needs further explanation 🙂
What is your favorite thing about living in Atlanta? What are some of your go-to spots for studying or hanging out?
I like the city vibe of Atlanta because it’s quite lively. Coda is definitely a nice workplace. I like hanging out at the Coda pool table, the apartment rooftop with an amazing city view & places mostly around Midtown.