I'm a recent Stanford Alum, with a BS and MS in Computer Science. I'm all about building impactful Artificial Intelligence, empowering women in tech, wilderness photography, singing and guitar, world travel, entrepreneurship, and fashion.
August 2021 - Present
Building intelligence for the next big thing.
June 2020 - September 2020
Deep Learning—Implemented key data sampling strategies which improved performance of the state-of-the-art stack. Collaborated with core engineering team on several PRs. Refactored and improved evaluation pipelines to increase compute and dev efficiency.
June 2019 - September 2019
Autonomous vehicles—Built an LSTM system using vehicle sensor data for an enhanced driving experience. As a bonus, my team won the company hackathon with a road quality monitoring/mapping system.
June 2018 - August 2018
Worked on Zero-Shot Multilingual Neural Machine Translation under Professor Rico Sennrich, and designed a neural network discriminator that used an adversarial objective function to universalize language representations during training.
June 2017 - September 2017
Computer vision and deep learning for object detection on a mobile platform. Using Caffe, trained deep learning frameworks from scratch to build gun detection capabilities on mobile. Achieved high accuracy on both gun and VOC classes in the same model.
Dive deep into my work, both professional and personal.
Reinforcement Learning
This paper aims to solve both a hierarchical reinforcement learning task and a collision avoidance problem for an autonomous rocket in a field of asteroids. This problem is modeled as a Markov decision process and uses the MAXQ decomposition and MAXQ-0 learning algorithm which are compared against Flat Q-learning.
Spoken Language Processing
We mitigate state-of-the-art models' tendencies to overfit by using a combination of augmentation techniques—making pitch, amplitude, noise, and vocal tract length perturbations, as well as time and frequency masking. All our experiments outperform the baseline in multiple speech recognition metrics.
Computer Vision
Preserving art is a test of time—often there are damaged/missing portions. With no references to how the painting was at its peak of creation, there lies a problem in creating truthful reconstructions of unique, rare art pieces. Utilizing Model Agnostic Meta Learning (MAML)on top of a CNN, we develop a regeneration model that accurately restores paintings, generalized across varying artistic complexity.
Knowledge Graphs
Get this—55% of users read online articles for less than 15 seconds. The general problem of understanding large spans of content is painstaking, with no efficient solution. We create a tool that generates analytical, concept graphs over text, providing the first-ever standardized, structured, and interpretable medium to understand and draw connections from large spans of content.
Let's get in touch.
Just shoot me an email,
or connect with me on LinkedIn.
San Francisco Bay Area
California
laurenzhu@alumni.stanford.edu
laurenzhu@cs.stanford.edu