0 BACK 0
PETER LILLIAN

p@pelillian.net

EDUCATION

University of Southern California

Master's

Aug 2018–Present (graduation May 2020)

(Progressive Degree Program)

Major: Computer Science

Bachelor's

Aug 2015–Present (graduation May 2019)

Full-Tuition Trustee Merit Scholarship

Major: Computer Science and Computer Engineering      Minor: Photography

3.7 GPA

On Executive Board as Project Coordinator at the USC Center for AI in Society CAIS++

EXPERIENCE

Internship: Robotic Embedded Systems Lab, USC Aug 2018–Present

Development in the cutting-edge of Reinforcement Learning. Currently working on the new release of the next-generation platform for RL research, Garage, aimed at making it much easier for RL researchers to quickly write, expand, and test new models.

Research: Lehrstuhl für Informationsmanagement im Maschinenbau (Cybernetics Lab), RWTH Aachen University, Germany May 2018–Aug 2018

Research in Reinforcement Learning applied to Robotics, as well as more general artificial intelligence research. Currently publishing a paper applying neuroscience methods to understand the Black Box problem and the internal organization of neural networks. Published my first paper.

Research: Kawasaki Disease Research Center, UCSD Aug 2017–Aug 2018

Research using the latest developments in Machine Learning (incl SVMs, Boosted Decision Trees, and Deep Neural Networks) to diagnose the rare childhood illness, Kawasaki Disease. Refining my models that already get higher accuracy than any other diagnosis method.

Internship: Breinify, Inc. May–Aug 2017

I implemented a system to retrieve aggregated data of specific individuals from graph databases. I then generated new insights based on this data with inference models, even creating a responsive web platform to visualize my work.

Research: USC Machine Learning Center Aug 2016–May 2018

Research into the latest machine learning algorithms to solve challenging problems, especially in computational biology and health care. Worked on improving models that diagnose diseases from symptom information. Also created models to analyze changes in biological neurons while the brain is learning.

Internship: BioBlocks, Inc. May–Aug 2016

I improved the speed/reliability of the BioBlocks database, adding new features—including a system writing procedures in English for Hungarian chemists & a system automating chemical supply/shipping logistics.

PUBLICATIONS

Author: Ablation of a Robot's Brain: Neural Networks Under a Knife arXiv 2018

It is still not fully understood exactly how neural networks are able to solve the complex tasks that have recently pushed AI research forward. We present a novel method for determining how information is structured inside a neural network. Using ablation (a neuroscience technique for cutting away parts of a brain to determine their function), we approach several neural network architectures from a biological perspective. Through an analysis of this method's results, we examine important similarities between biological and artificial neural networks to search for the implicit knowledge locked away in the network's weights.

SKILLS

Development: Python(incl numpy/sklearn/matplotlib), Keras, Tensorflow, Java, C++, HTML, CSS, Javascript, SQL, PipelinePilot, Apache Tomcat/Java EE Webserver

Programs: Adobe Photoshop, Illustrator, AfterEffects, Premiere

INTERESTS

Artificial Intelligence, Photography, Graphic Design/Typography/Drawing, Backpacking/Camping, Sailing, Skiing

0 BACK 0
A A A