Michael Sun

Hi! I am an aspiring AI researcher and below are my portfolio projects.

If you’re looking for my LinkedIn, or GitHub, you’ll be redirected. See my resume here. Reach out to me at msun415@stanford.edu if you want access to the private repos (projects listed here but not on my GitHub).

UPDATE: I’m currently interning in the Think Tank Team at Samsung Research America through summer 2020. I may also work part-time for a startup. I’m also running some non-technical side projects like this and this. There’s also some other stuff. I’m pretty cramped through the summer. I MAY take a fall quarter leave of absence (Sept 4 – Dec 23, 2020) off if there’re exciting opportunities. If you have exciting opportunities for me, please reach out!

Major Project Experience (to date)

For each of these, see “Longer Summaries” section for more details!

Machine Learning Internship @ Samsung Research America (Think Tank Team)

  • Not sure how much I can share yet but psst

Stanford QIAI Deep Learning Research (supervisor Daniel Rubin)

  • Applying techniques of multi-modal representation learning on chest X-ray images, following this dataset with ideas from this paper (some initial code)
  • Training object detection models on Stanford’s largest video/EEG dataset for seizure detection, using this to track patients and eventually this for event composition

Machine Learning Internship @ Synaptics – Deploying an end-to-end video object detection pipeline for detecting logos on Synaptics VSR 371 system-on-chip based on this paper (see more under “Longer Summaries” section)

Quizkly (Live app)– Full-stack React + Django web app with end-to-end deep learning pipeline that auto-generates quizzes from any corpus of text

aiRoute (App Store) – iOS native app that randomly generates a running route in your area and provides turn-by-turn map and voice navigation

aiFood (App Store) – iOS native app that automates macro-counting and meal preparation with custom made API

Course Final Projects

PixelCNN (GitHub) – Experimentation/evaluation of better ways to project caption embeddings for the PixelCNN conditional generative model (written report) (poster)

KnowledgeTree (GitHub) – Console C++ and Python application that builds a high-to-low level concept tree from scraping Wikipedia pages with NLP techniques (poster)

GoodNews (GitHub)  – Machine learning project that predicts news article virality and popularity using its content and metadata (written report) (poster) (code)

aiFriend (GitHub) – Website that generates reports (in R Markdown) analyzing and visualizing Messenger conversations (sample report) (code)

Longer summaries

(Each synopsis is divided into categories that I think best delivers the logical flow of the project, not necessarily chronological or rigid in format.)

Major projects:

Samsung Research (Internship)

Research at Stanford QIAI (RAship)

Synaptics (Internship)

aiRoute

aiFood

MealApp (API for aiFood)

Quizkly

Course final projects (only wrote one cause the rest have reports attached):

KnowledgeTree

I am an undergraduate at Stanford University, pursuing Mathematical and Computational Science with honors, expected 2022. I expect to graduate 2023 with a Masters in Computer Science.

Below is a more comprehensive record of everything I’ve done.

In high school:

  • Awarded Second Place Grand Award in Mathematics Category at Intel International Science and Engineering Fair 2017
    • Project was a conjecture and proof of new upper bounds on the metric dimension for planar graphs with applications to GPS-less navigation systems
  • Scored 14 on the 2017 United States of America Mathematical Olympiad (ranking me around top ~110 nationwide)
  • Co-authored of a paper in combinatorial graph theory on the Metric Dimension for Planar Graphs, readable here: [1704.04066] Bounds on metric dimension for families of planar graphs
  • Achieved Distinguished Honor Roll Recipient on both AMC 12 and AMC 10 (top 1% on the nation’s largest math competition)
  • Ranked top 30 in the national American Invitational Mathematics Examination (the invitation round after the AMC), an invitation-only round for the US Math Team selection process
  • Attended Ross Mathematics Camp at Ohio State University 2018 (one of USA’s oldest pure math summer program and an intense 6-week study of number theory)
  • Started school’s only math club, growing the club in three years to having twenty regular members, lecturing on a weekly basis on a topic of interest, hosting contests and activities, and promoting math at school assemblies
  • Started a collaborative blog  for competitive math students training for Olympiads and became one of the most popular blogs on the Art of Problem Solving, an online forum for math problem solvers around the world

In college:

  • Selected in the two dozen cohort among hundreds of entrepreneurial-inclined Stanford students to be in this year’s Pear Garage program
  • Published two end-to-end iOS apps on the App Store
  • Started Quizkly with a partner, a machine learning EdTech product being user tested by Stanford Medical Students
  • Doing deep learning research with at the Rubin Lab in medical imaging (current topic is on multi-modal weak supervision)

I am also alumni of the following programs:

  • Summer Program on Applied Rationality and Cognition 2018 – a highly selective program, took classes in cognitive science, psychology and artificial intelligence under famous academics
  • Make School Summer Academy 2018 – completed curriculum in iOS App Dev using Swift 4 and Xcode, took courses in need-finding, web dev, continuous deployment, APIs, and much more
  • AwesomeMath Summer Program twice – an Olympiad-prep math camp

Contact

Get in Touch

Stanford University
450 Serra Mall
Stanford, California 94305
USA

Send Me a Message