Small Simplicity

Understanding Intelligence from Computational Perspective

About me

profile


cv @cocoaaa projects

Hello! I'm a PhD student at University of Southern California (USC) in Computer Science, studying the dynamics of neural networks using information-theoretic approach and extracting lower dimensional representation of complex, unstructured geospatial datasets like multi-spectral satellite images.

Research interest

  • the interpretability and transferability of deep neural networks, and
  • hybrid intelligent systems that incorporate knowledge-based (symbolic) AI to neural networks

At USC, I'm working with Prof. Yao-Yi Chiang at the Spatial Computing and Informatics lab and Prof. Craig Knoblock at ISI's Center on Knowledge Graphs.

Before USC, I studied at Massachusetts Institute of Technology Mathematics and Electrical Engineering and Computer Science (EECS) for my Bachelors and Masters. During my Masters, I concentrated on Artificial Intelligence and worked under the joint guidance of Professor Regina Barzilay, Professor Wojciech Matusik, and Dr. Julian Straub. My main projects were (1) image registration of mammograms for breast cancer detection, and (2) 3D reconstruction of human arms for efficient lymphedema screening. You can find out more about them here

My current projects focus on using reasoning and deep neural networks to understand complex spatio-temporal data collected from satellites.

Please see my project page for more details.


Knowledge representation in Learning and Generalization

Lingering questions

In a bigger scheme, I am excited about the problems regarding human perception of the world and how symbolic representation of knowledge can facilitate learning in a new domain [via knowledge transfer across various domains/modalities]. I'm continuously exploring these questions in my research:

  1. How can intelligent agents learn with less supervision, particularly in the domain of vision and three-dimensional perception (:spatial reasonging?)
    • via autonomously interacting with the environment
    • via incorporating external knowledge
    • via incorporating common sense reasoning

My current project on road detection from satellite images explores this question using external geospatial knowledge base (OpenStreetMap) and reinforcement learning.

  1. How can those knowledge be represented in a more abstract form so that it can be used for learning in different domains (keyword: Knowledge Representation, Transfer Learning/Domain Adaptation)

Softwares

I use Python (eg. PyTorch, Numpy, scikit-learn) for machine learning projects and C++ for hardware systems (eg. Microsoft Kinnect and Intel RealSense) as in this project.


Besides working on my projects, I enjoy being in nature and trying out different sports. Along the way, I became a certified scuba diver and have sky-dived in Czech sky! I enjoy biking and swimming -- they help me connect to the dimension that is not about thinking and analyzing, and remind me we are more than our thoughts and minds. I enjoy sharing such experiences with friends:)