Nice to meet you!
I'm James Fu 👋Hello! I'm James Fu 👋
I'm James Fu 👋
A current M.S. Data Science student @ UT Austin. I aim to deepen my understanding of various machine learning methodologies.
About Me
💙 🐻
This past year, I graduated from UCLA with a B.S. in Computational Biology (Data Science concentration), where I developed a strong foundation in data science and software engineering, with a particular focus on NLP, design, and biotech applications. I'm mainly proficient in Python, but I occasionally dabble in languages like C++, JavaScript, SQL, and R.
👾 🤘
I'm a current Master's student at UT Austin studying Data Science, where I'm learning about transformer architectures like BERT and how they can be used to build LLMS, and enhancing my skills in data analysis and statistical methods and data.
⚙️ 🍵
Over the past 7+ years, I’ve worked on various coding projects, with a focus on Python and full-stack development. I'm also seeking full-time opportunities in Data Science, Analytics, Software Engineering, or any related field. If I'm not at my computer, you'll find me in the kitchen trying new recipes and recreating viral cafe drinks, or outside playing tennis.
Projects
Zipursky Lab, UCLA CaSB Thesis
Gene Expression and Subtype Analysis of Astrocytes in the Mouse Brain
Developed a pipeline using unsupervised machine learning to identify six astrocyte subtypes through spatial clustering of spatial transcriptomic data from the Allen Mouse Brain Atlas, discovered 104 astrocyte-specific genes through differential expression analysis with Bonferroni correction across 10+ million cells.
NLI Cartography Study, UT Austin CS388
Enhancing Robustness in Natural Language Inference Models
Followed-up on methods explored in Swayamdipta et al. (2020) to improve NLI robustness. Fine-tuned ELECTRA-small using dataset cartography and contrast sets with distractors, reweighting hard-to-learn examples during training to reduce artifacts. Achieved an 8% accuracy increase on novel contrast sets.
Faircare, LA Hacks 2024
Developing Faircare for Transparent Pricing
A healthcare cost modeling website that leverages machine learning and deep learning to generate synthetic data and make accurate cost predictions. It provides intuitive visualizations summarizing fair treatment cost estimates, ensuring transparency for all users, regardless of insurance coverage.
Dotmentia, Los Altos Hacks IV
Dementia Care via Voice Assistance and Facial Recognition
Won 1st place by building Dotmentia, an assistive AI system that leverages facial recognition (OpenCV) and Google Assistant integration (DialogFlow) to help dementia patients recognize family members and those around them in real-time, enhancing their daily interactions and independence.
Skills
Python
PyTorch
TensorFlow
Pandas
SQL
scikit-learn
Tableau
Git
React
Get in touch
Let's talk
I'm currently looking for full-time opportunities in Data Science, Analytics, Software Engineering, or any related field. I'd be happy to further discuss my experiences with you, simply shoot me an email or fill out the form below.
jamesfup@gmail.com
+1 (925) 875-8886
Bay Area, CA