Xin Yu (Dennis) Tan

My name is Xin Yu (Dennis) Tan, and I am a UC Berkeley alumnus who graduated in December 2017 with a Bachelors of Science in Electrical Engineering and Computer Science.

I'm a very passionate individual willing to spend hours upon hours on projects that I care about. I want to bring to life the impossible ideas that will revolutionize how we experience this world.

Some of my interests in computer science include:

- artificially intelligence and machine learning

- robotics and computer vision

- UI/UX in mobile, web, and game development

I'm also a very enthusiastic participant in changing society via community service, in particular in the education domain. It's my dream that one day everyone can have access to quality education via a digital platform that is both scalable and self-sustainable.

Xin Yu Tan

I did research in robotics and deep reinforcement learning at UC Berkeley's Robotics Learning Lab (RLL) under the supervision of Professor Pieter Abbeel. I worked with PhD student Chelsea Finn and postdoc Sergey Levine to co-author an ICRA 2016 paper on deep spatial autoencoders:

Deep Spatial Autoencoders for Visuomotor Learning

Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel

[webpage] [pdf] [arXiv]

I also developed the user interface for the open source Guided Policy Search repository, which is used by numerous researchers in RLL and other labs.

As part of a deep learning graduate class at UC Berkeley, I co-authored a paper with Andrew Liu on using appearance features from the person re-identification task in object tracking of general objects in the YouTube BoundingBoxes dataset:

Generalized Appearance Features for Object Tracking

Andrew Liu, Dennis Tan

[poster] [pdf] [github]

I was an artificial intelligence intern at Stotter Henke Associates Inc., an artificial intelligence solutions contracting company. There, I worked on feature extraction from radar and EO/IR data of simulated lethal objects in space, as part of a Missile Defense Agency contracted project. I was also a software engineering intern at Box Bot Inc., a last-mile autonomous delivery start-up. There, I worked on sensor calibration and integration for robot localization, and I also integrated ORB SLAM2, a simultaneous location and mapping solution, into the autonomous vehicle's path-planning algorithm.

I've contributed to multiple programming projects. Currently, I am working on a 2D real-time strategy Android game called League of Legions, where players strategically maneuver different colored pixel armies to battle for dominance. I was the lead programmer for Cyan Knight, a 2D platformer game developed using Unity 3D game engine. I've also worked on a personal project called Chess 1.0, which used Java and Swing to develop a two-player chess program compliant with all the rules of chess.

I'm also active in community service, especially in the education domain. I was the president of Berkeley ANova, a student organization dedicated to improving computer science education in low-income communities across the Bay Area. I also was the webmaster for Cal Rotaract, a community service organization that hosts weekly events such as restoring natural areas, helping the homeless, and much more. I used to be a lab assistant for UC Berkeley's data structures class CS 61B.




Resumes: [Machine Learning] [Software Engineering]