About Me
I am a third year graduate student at Rice University. I am advised by Dr. Anastasios Kyrillidis, and I work closely with Dr. Geoffroy Hautier, as well as Dr. Christopher Jermaine, Dr. Thomas Reps of UW-Madison, Dr. George Phillips, and Dr. Mitchell Miller.
My work focuses in three areas:
1) the development of novel Neural Network (NN) architectures,
2) applying NNs to the physical sciences: specifically atomistic structural calculations in nanoengineering and biochemistry,
3) Reinforcement Learning (RL) based model tuning and Reinforcement Learning from Human Feedback (RLHF)
Throughout my work I focus on the underlying mathematics of the application domain and customizing the NN architecure to encode inductive biases into the architecture. Additionally, due to the nature of the ML for physical sciences domain, a substantial part of my work in that area is in cross-departmental collaboration, developing and integrating NN pipelines and utilities, and data curation.
For an up-to-date resume including internships, awards, etc, please feel free to contact me!
I started writing some explanatory articles covering in detail the mathematics of machine learning. Check them out!
Explanatory Posts
Transformers and Related
- Reinforcement Learning from Human Feedback Introduction pdf
- Transformer Mathematics In Extensive Detail pdf
- Deep Dive Into Attention Computations pdf