Donald Bertucci
I am a junior at Oregon State University studying Computer Science and Mathematics.
I create interactive systems that help people visualize and interpret machine learning models that use a ton of data.
Broadly speaking, I'm focused on how humans can better understand machine learning model behavior. Complex structures and how they act blow my mind: both machine and animal.
Education
2020 – Present
B.S. Computer Science
Oregon State University
Degree focus on Artificial Intelligence
Experience
Sep. 2022 – Present
Carnegie Mellon University
Research Assistant, CMU Data Interaction Group (DIG)
Developing methods to interactively discover systematic errors in ML models within Zeno
with Ángel Alexander Cabrera
and Adam Perer
.
Enabling scalable visualization of Big Data within Falcon
with Dominik Moritz
.
Summer 2022
Carnegie Mellon University
Research Intern, HCII Summer Undergraduate Research Program
Researched methods to discover where ML models fail [_].
Primarily advised by Ángel Alexander Cabrera and Adam Perer . Also advised by Nari Johnson and Gregory Plumb . Summer program led by Laura Dabbish and I was hosted by the CMU Data Interaction Group (DIG) .
Primarily advised by Ángel Alexander Cabrera and Adam Perer . Also advised by Nari Johnson and Gregory Plumb . Summer program led by Laura Dabbish and I was hosted by the CMU Data Interaction Group (DIG) .
Aug. 2021 – Aug. 2022
Oregon State University
Research Assistant, Data Interaction and Visualization (DIV) Lab
Created interactive user interfaces to visualize large data and machine learning models.
Designed, implemented, and evaluated interactive interfaces [_, _]. Advised and mentored by Minsuk Kahng
.
Summer 2021
Oregon State University
EECS REU Summer Cohort
Discussed, presented, and improved research communication to CS faculty and students [_]. Program led by Alan Fern
.
Feb. 2021 – May 2021
Oregon State University
Research Intern, URSA Engage Research Program
Created interactive interfaces to visualize difficult topics in artificial neural networks [_]. Designed interactive systems for visualizing model comparison. Hosted by the DIV Lab
and Minsuk Kahng
.
Publications
Conference
C2
DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine
Donald Bertucci
, Md Montaser Hamid
, Yashwanthi Anand
, Anita Ruangrotsakun
, Delyar Tabatabai
,
Melissa Perez , Minsuk Kahng
Melissa Perez , Minsuk Kahng
IEEE Transactions on Visualization and Computer Graphics (IEEE VIS 2022). Oklahoma City, OK
C1
Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL
Kin-Ho Lam
, Delyar Tabatabai
, Jed Irvine
, Donald Bertucci
, Anita Ruangrotsakun
, Minsuk Kahng
, Alan Fern
32nd International Conference on Automated Planning and Scheduling (ICAPS 2022).
Workshop
W2
Backprop Explainer: Interactive Explanation of Backpropagation in Neural Network Training
Workshop on Visualization for AI Explainability (VISxAI, IEEE VIS 2021).
W1
An Interactive Introduction to Autoencoders
Workshop on Visualization for AI Explainability (VISxAI, IEEE VIS 2021).
Poster
P1
Mirror: Interactive Discovery of Blindspots in Machine Learning Models
Human-Computer Interaction Institute (HCII) Summer Research Showcase (2022). Pittsburgh, PA
Public
Talks – DendroMap
| Full paper presentation at IEEE VIS 2022 in Oklahoma City, OK
Talks – Backprop Explainer
| Workshop on Visualization for AI Explainability (VISxAI, IEEE VIS 2021)
| Celebrating Undergraduate Excellence (CUE, 2021) at Oregon State University
| EECS Undergraduate Summer Cohort at Oregon State University
Reviewing – VISxAI Workshop
| VISxAI 2022 Program Committee Member
References
Dr. Minsuk Kahng – Research Scientist
People + AI Research (PAIR)
Google Research
Dr. Adam Perer – Assistant Professor
Data Interaction Group (CMU DIG)
Carnegie Mellon University
Alex Cabrera – PhD Student
Human-Computer Interaction Institute (HCII)
Carnegie Mellon University