I'm a PhD candidate in EECS at UC Berkeley. I'm part of the Berkeley AI Research Lab. I'm interested in machine learning for control and safety-critical control.
I received my M.S. in Machine Learning from Carnegie Mellon University and B.S. in EECS from UC Berkeley.

In the past, I've worked on multi-agent collision avoidance, learning from demonstration, human behavior learning, optimal control, hybrid systems, and hierarchical planning in CMU Machine Learning Department and the Berkeley AI Research Lab.

Publication

Conference

Jennifer C. Shih et al. Reachability-based Safe Planning for Multi-vehicle Systems with Multiple Targets, 2020 (submitted)
Jennifer C. Shih et al. A Framework for Online Updates to Safe Sets for Uncertain Dynamics, IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2020
Jennifer C. Shih, Predicting Stochastic Human Forward Reachable Sets Based on Learned Human Behavior, American Control Conference, July 2019
Aparna Dhinakaran*, Mo Chen*, Glen Chou, Jennifer C. Shih, Claire J. Tomlin, A Hybrid Framework for Multi-Vehicle Collision Avoidance, 56th IEEE Conference on Decision and Control, Dec 2017
Mo Chen*, Jennifer C. Shih*, Claire J. Tomlin, Multi-Vehicle Collision Avoidance via Hamilton-Jacobi Reachability and Mixed Integer Programming, 55th IEEE Conference on Decision and Control, Dec 2016
(* Equal contribution)

Teaching

UC Berkeley CS100/200 Principle and Techniques of Data Science
Spring 2020: Head Content TA
UC Berkeley CS189/289A Introduction to Machine Learning
Fall 2019: Teaching Assistant
Carnegie Mellon University Introduction to Machine Learning
Spring 2018: Teaching Assistant
UC Berkeley EE16A Designing Information Devices and Systems I
Spring 2016: Content TA, Fall 2015: Discussion TA
UC Berkeley CS61B Data Structures and Advanced Programming
Fall 2013: Discussion & Lab TA

Service

Reviewer for American Control Conference (ACC),
Conference on Decision and Control (CDC),
European Control Conference (ECC),
International Conference on Intelligent Robots and Systems (IROS)

About

University of California, Berkeley

Ph.D. in Electrical Engineering and Computer Sciences,
GPA: 4.0/4.0

Carnegie Mellon University

M.S. in Machine Learning '18, GPA: 4.03/4.3

University of California, Berkeley

B.S. in Electrical Engineering and Computer Sciences '16, Technical GPA: 3.93/4.0
Awards & Honors:
Machine Learning Department Teaching Assistant Award (2018)
Outstanding Course Development and Teaching Award (2016)
UC Berkeley EECS Honors Degree Member (2015-2016)
Eta Kappa Nu EECS Honor Society (2014)
Edward Kraft Award for Freshmen (2013)

Interests:
I like to travel and learn to make good food.

Some courses I've taken:
Machine Learning / AI:
Advanced Introduction to Machine Learning
Statistical Machine Learning
Deep Reinforcement Learning
Statistical Techniques for Robotics
Machine Learning for Large Datasets
Computer Vision
Artificial Intelligence

Probability & Statistics:
Intermediate Statistics
Probability and Random Processes
Concepts of Probability
Concepts of Statistics

Optimization:
Convex Optimization
Convex Optimization and Approximation
Optimization Models in Engineering
Math Methods for Optimization

Control theory:
Linear Systems Theory
Nonlinear Systems