Hey I'm Bowen! I an M.Eng student in the MIT EECS department with a B.S. degree in EECS and physics (also from MIT). I am currently working in Media Lab's Camera Culture group on meta-modeling techniques for deep learning, but I am also interested in machine learning for health and economics, robotics, and meta-modeling in general.
Designing Neural Network Architectures Using Reinforcement Learning
We model Convolutional Neural Network (CNN) architecture selection as a Markov Decision Process. The system can be distributed across many machines and generates models that out perform all others that use the same layer types. Caffe code for the top models generated can be found on my github, and the paper can be found on arxiv or the openreview site for ICLR 2017. I recently gave a presentation on the paper for the CSAIL Vision Group, and our work was recently featured in the MIT Technology Review!
Consumer Credit Risk Modeling
We analyze the performance of various machine learning algorithms, namely decision trees, random forests, and logistic regression, on predicting consumer credit delinquency. Our data included time-series transactions, credit bureau reports, and internal bank profiles for each customer. The results show that any of these methods far outstrips the current heuristic for credit delinquency, credit score, as shown in my report.
Determining the resolution limits of electron-beam lithography
Our work focused on better characterizing the point-spread-function (PSF) of the electron beam in electron beam lithography. I developed Monte Carlo simulations to simulate the PSF for comparison with my team's empirical results. Our work was published in Nano Letters in 2014.
H to ZZ to 4l
During the Large Hadron Collider's (LHC) upgrade in 2013, I worked with the Compact Muon Solenoid group to study and verify that the Higgs Boson to ZZ Bosons to 4 lepton decay channel could continue to be detected under increased LHC luminosity and power. Our work was published in a public CERN analysis note.
I am a co-founder at Perch. We are an early stage weight room analytics startup and went through the MIT delta v accelerator last summer (2016). I work on machine vision, rep tracking algorithms, and most other aspects of the product back-end.
I was a Data Science Intern at Quora in the summer of 2015. I worked on identifying and fixing categorically misused topics, improving automated topic labeling, and exploring topic geometries. I also helped in creating metric dashboards, responding to company data inquiries, and fixing bugs in data logging.
I was a Data Science Intern at AgilOne during my 2014 Summer break. I created a framework for validating customer data before running the machine learning models. On top of this, I built a deployment framework that would automatically select features to use and initialize models for new customers. I also did some minor work on the product front end.
The Kinect 2-Chain was a project I worked on for HackMIT 2015. The goal of the project was to aid the visually impaired in navigation. We used a Kinect 2 to map the space in front of the user and send stereo audio signals with varying pitch to indicate the direction and distance of obstacles. We also used a deep learning API so that the user could also request that a description of the scene in front of them be read aloud. We took 2nd place overall and also won the Microsoft prize; some news coverage can be found here.
MIT Robotics Team
I co-founded the MIT Robotics Team in late 2013. I led the software team for 2 years, during which we placed 2nd in the 2014 NASA RASC-AL ROBO-OPS Competition and competed in the 2015 NASA Sample Return Centennial Challenge.