United States
Hello! I'm Jenny, and I am currently pursuing a Master’s in Computer Science at Stanford University, specializing in artificial intelligence and algorithms. I’m excited to continue exploring diverse areas within AI and computer science at Stanford, with the goal of transforming cutting-edge technologies into impactful, real-world solutions.
CS 2800 Discrete Structures: - Lead discussion sections of 30+ students weekly - Support students on homework problems in office hours weekly
General description: Our project mainly uses Variational Quantum Algorithms (VQAs) to solve optimization problems such as Semi-definite Programs (SDPs). VQAs use quantum computers to evaluate the cost function and classical computers to optimize. In this way, VQAs use the strength of both quantum and classical worlds. Our project proposed a novel way to reformulate SDPs by introducing slack variables to optimize primal and dual. Our method sandwiches the true optimal value from above and below, and I am responsible for the simulation experiments and teaching high school students in our lab. - Implemented algorithms in Python using various quantum computing libraries such as PennyLane, Qiskit, and Qulacs - Engineered a maintainable code structure to enhance code readability and modularity - Sped up the simulation by 1000+ times using Numpy - Visualized and processed simulation results using Matplotlib - Developed lectures and assignments for two high school students to learn optimization, quantum computing, and programming - Presented this work at APS March Meeting 2024, section B51.010
General description: Our project aims to use Quantum Machine Learning (QML) to distinguish whether a quantum input has high or low entanglement. - Implemented quantum convolutional neural networks using both Python and Julia - Designed QML models by generalizing classical machine learning concepts to quantum computing with high accuracy on certain datasets
CS 4820 Introduction to Analysis of Algorithms: - Developed review materials, videos, slides, and logical proofs on Divide and Conquer, Network Flow, Complexity Theory, and Dynamic Programming. - Wrote sample solutions to homework problems, practice problems, and exam problems - Created homework and exam rubrics, supervised grading for up to 400 students - Supported 10+ students and clarified questions on virtual discussion board and office hours weekly
General description: The quality and diversity of data are very important in machine learning. In the area of autonomous driving, corner case data such as vehicle turnover is very hard to collect. Therefore, this project aims to use synthetic data generated by Generative Adversarial Networks (GANs) to help increase the accuracy of the model for corner cases. - Programmed various models for photorealism, photo enhancement, and style transfer - Trained a GAN using PyTorch and finetuned its parameters to generate more than 1000 high-quality data