Donglei Cai

• Applied self-supervised pre-training (contrastive learning, masked autoencoders) for multi-view echocardiogram video classification, improving downstream cardiac diagnosis accuracy by 16% on 10,000+ echocardiogram videos with limited labeled data.

• Co-developed Plenoptic Tunnels (SIGGRAPH Asia 2022 submission)

• Developed introductory data science/machine learning lessons and technical workshops for beginners • Taught weekly lessons and mentored students new to data science/machine learning and hosted workshops every semester

Highest rank: 763rd place out of 177000+ competitors • Kaggle Profile: https://www.kaggle.com/derekcai • BirdCLEF 2021 - Birdcall Identification Rank: 7/816 • SIIM-FISABIO-RSNA COVID-19 Detection Rank: 20/1305 • SETI Breakthrough Listen - E.T. Signal Search Rank: 27/768

• Built data pipelines processing 20M+ rows of 15-minute interval network telemetry across 2,000+ network elements — LSTM/1D-CNN time series models for 24h/48h load forecasting with scalable recurring refit, and binary classifier for 12-hour outage prediction enabling proactive network issue detection.

CS 61A The Structure and Interpretation of Computer Programs CS 61B Data Structures CS 61C Great Ideas of Computer Architecture (Machine Structures) CS 189 Machine Learning CS 194-26 Introduction to Computer Vision CS 280 Computer Vision EECS 16B Designing Information Devices and Systems II EECS 127 Optimization Models in Engineering DATA 100 Principles & Techniques of Data Science DATA 102 Data, Inference, and Decisions MATH 53 Multivariable Calculus MATH 54 Linear Algebra and Differential Equations MATH 55 Discrete Mathematics MATH 104 Introduction to Analysis MATH 110 Linear Algebra MATH 128 Numerical Analysis MATH 185 Complex Analysis STAT134 Concepts of Probability STAT135 Concepts of Statistics STAT150 Stochastic Process STAT153 Time Series STAT155 Game Theory