I am a Master's student in Computer Science, Artificial Intelligence track at Stanford University. I am experienced in data analysis, machine learning, and deep learning, and have done relevant projects in the areas of computer vision, healthcare, image processing, sports, and more. I am passionate about responsible usage of AI and analyzing human-AI interaction. Please feel free to reach out via email - I love talking about my projects!
Bounding box regression and classification on over 3000 scanned, expert-labeled images of Japanese calligraphy pages. Objective is OCR on Japanese calligraphy. I researched multiple architectures in the image-to-text domain, from R-CNN techniques to image captioning architectures. Baseline model is a CNN with VGG-19 feature extraction that serves as an encoder, which is then fed into a LSTM decoder with self-attention. Baseline results have approx. 40% training classification accuracy. Currently working on Faster R-CNN bounding box regression approach.
Implemented multiple classification algorithms and signal processing techniques on the UCI Epilepsy dataset. Baseline models included softmax regression and k-nearest neighbors, which achieved moderate accuracy. Best model was a 1D CNN, borrowing from a text sequence classification architecture. Algorithms were tested based on raw time-series data as well as frequency data extracted by the Fourier transform and the spectral entropy of the singal. My contribution to the group was proposing and implementing the Fourier transform as a feature extraction technique, and creating a Hidden Markov Model for classification.
Built on NVIDIA's Vid2Vid photorealistic video-frame generation architecture, trying a transfer learning approach to few-shot. My contribution was desgining and implementing a novel training scheme that refined pre-trained generator weights by minimizing various divergences (L1, L2, SSIM) between unseen images and the generator output. Results showed high optical stability but low realism: the model was generally able to learn the location of objects, but not the appearance.
Implemented Caesar cipher and Vigenere cipher encryption and decryption tools. Created a stream cipher analysis tool, and a stream cipher solver for attacking multi-time pads (key resuage) based on maximizing the number of alphanumeric character "hits" given proposed key bits.
Implemented a chess engine (minimax agent) and GUI in Java, with AI vs. AI, human vs. AI, and human vs. human modes.
Implemented Canny and Sobel edge detection algorithms in C++.
Led 2 labs of ~20 students each in the Artificial Intelligence course at Stanford Pre-Collegiate Studies, reviewing concepts like search algorithms, game-playing algorithms (e.g. minimax), and reinforcement learning. Supervised and advised projects in computer vision, price prediction, sentiment analysis, and more. Wrote problem set and code solutions (Python and Unity C#) for student reference.
Intern for Dr. Michael McCullough. Developed business strategy and execution for his non-profit ventures.
Project 1: stealth
Supervised a remote team of 6 interns from Harvard and Stanford, managing deadlines, workflow, conflict resolution, etc. Organized market research about attractive markets for quickly commercializing new healthcare technology. Analyzed disjoint and vague data/business reports in English, Spanish, Japanese, and Chinese.
Project 2: BrainMind
Front-end web development for our website. Developed a custom email-automation marketing script for internal use. Researched top neuroscience companies and influencers in the field.
Project 3: RegenMed Systems
Contributed to market validation for the hematopoietic stem cell/bone marrow market. Researched the hematopoietic stem cell/bone marrow supply chain Identified use cases and market sizes for various applications of hematopoietic stem cells/bone marrow
Project 4: Global Leadership IncubatorCoordinated and standardized the admissions process for scholars seeking higher education in the U.S. via the Global Leadership Incubator's scholarship and sponsorship program Conducted video-call interviews with prospective candidates. Reviewed, evaluated, and redesigned the organization website UI/UX.
Though I consider an afternoon spent on arXiv with a large cup of coffee to be an excellent leisure activity, when not thinking about AI, I enjoy making music. I am a jazz pianist and songwriter, and am heavily involved in the music side of musical theatre at Stanford.
My past musical theatre credits include Gaieties 2019: Midterm Impossible (Composer, Lyricist, and Music Director), Cabaret (Pianist), The Addams Family (Pianist), Gaieties 2018: Jane Stanford and the Chamber of Secrets (Pianist), The Wiz (Music Director and Pianist), Gaieties 2017: Bearanormal Activity (Pianist), Ragtime (Rehearsal Pianist), and Pippin (Assistant Producer).
Other interests include bullet chess (find me @tchainzzz), watching sports, and getting 8 hours of sleep every night -- it's really good for productivity!