Donny Bertucci

Previously Computer Science PhD student at Georgia Tech and Computer Science and Math undergrad at Oregon State University .

In the past, I've worked on visualizing neural networks, analyzing protein function, large scale data analytics, machine learning model interpretability, and explainable AI at the GT Visual Analytics Lab , OSU Venom Biochem Lab , CMU Data Interaction Group , and OSU DIV Lab .

Education

Ph.D. Computer Science

Georgia Institute of Technology
Machine Learning and Visualization
**Dropped out as of Nov. 2024

B.S. Computer Science

Oregon State University
Degree Focus: Artificial Intelligence, Minor: Mathematics

Experience

Georgia Institute of Technology

Graduate Research Assistant, GT Visual Analytics Lab
Researched ML for Bio and explainable AI [_, _, _, _]. Advised by Dr. Alex Endert .

Oregon State University

Research Engineer, Venom Biochemistry and Molecular Biology Lab
Designed an interface with protein visualization and implemented computational analysis methods to discover protein function for venom proteins [_]. Advised by Michael Youkhateh and Dr. Nathan Mortimer .

Carnegie Mellon University

Data Visualization Research Intern, CMU Data Interaction Group (DIG)
Researched interactive methods to improve language model prompt generation and transparency with Dr. Adam Perer . Developed interactive visualizations of neural network compression/quantization error [_].

Carnegie Mellon University

Research Assistant, CMU Data Interaction Group (DIG)
Developing human-centered ways to evaluate Machine Learning model behavior within Zeno [_] with Dr. Alex Cabrera . Enabling linked visualizations at scale with FalconVis [_] with Dr. Dominik Moritz .

Carnegie Mellon University

HCII Summer Undergraduate Research Program
Developed user interfaces to interactively discover poor behavior in neural networks [_]. Advised by Dr. Alex Cabrera and Dr. Adam Perer . Hosted by the Data Interaction Group (DIG) .

Oregon State University

Research Assistant, Data Interaction and Visualization (DIV) Lab
Developed user interfaces to visualize large data and interpret complex machine learning models [_, _]. Mentored and advised by Dr. Minsuk Kahng .

Oregon State University

URSA Engage Research Program
Developed interactive interfaces to visualize difficult concepts in learned neural networks [_, _]. Advised by Dr. Minsuk Kahng .

Research

[16]

VQ-VAE Explainer: Learn the VQ-VAE Implementation with Interactive Visualization

Donald Bertucci and Polo Chau
Interact with and visualize a VQ-VAE (Vector-Quantized Variational Autoencoder) directly in the browser.
[15]

Explore ARC-AGI

Donald Bertucci
Visualize the ARC-AGI dataset with live crossfiltering for compression metrics.
[14]

VAE Explainer: Supplement Learning Variational Autoencoders with Interactive Visualization

Donald Bertucci and Alex Endert
Interact with and visualize a Variational Autoencoder directly in the browser.
[13]

DS569k Protein Embeddings Dataset

Donald Bertucci and Alex Endert
ProteinCLIP embeddings for ~569k proteins from UniprotKB.
[12]

Venome: A System to Store and Analyze Venom Protein Function

Donald Bertucci , Ansen Garvin , Cora Bailey , Amanda Sinha , Michael Youkhateh , and Nathan Mortimer
A site where you can upload, search, compare, and analyze Venom Lab proteins + create interactive articles.
2024 Engineering Expo (Computer Science Capstone Project), Oregon State University. Corvallis, OR
[11]

Random Number Generator with Elementary Cellular Automata in Matlab

Donald Bertucci
Random numbers with Elementary Cellular Automata Rule 30 in Matlab + transform to any other distribution.
Mathematical Software with Torrey Johnson, Oregon State University. Corvallis, OR
[10]

ProteinScatter: Visualizing Fragments of Structurally Similar Proteins with a Scatterplot

Donald Bertucci
Converted proteins to Foldseek 3Di, then trained an auto-regressive transformer. Embeddings converted into a 2D scatterplot.
Molecular Modeling with Juan Vanegas, Oregon State University (2024). Corvallis, OR
[9]

Visualizing Neural Network Compression

Donald Bertucci and Adam Perer
An interactive article exploring how model compression error affects neural network behavior.
[8]

FalconVis: A Library to Cross-Filter Billions of Data Entries on the Web

Donald Bertucci and Dominik Moritz
A JavaScript library for visualizing big data on the web with your custom visualizations and scalable data formats.
[7]

Finding the Distance Function in the Poincaré Disk using Stereographic Projection

Donald Bertucci
A paper that derives the Poicare disk distance function using stereographic projection from Minkowski Space.
Non-Euclidean Geometry with Tevian Dray, Oregon State University (2023). Corvallis, OR
[6]

Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning

Alex Cabrera , Erica Fu , Donald Bertucci , Kenneth Holstein , Ameet Talwalkar , Jason I. Hong , and Adam Perer
ACM Conference on Human Factors in Computing Systems (CHI). Hamburg, Germany, 2023.
[5]

DendroMap: Visual Exploration of Large-Scale Image Datasets for Machine Learning with Treemaps

Donald Bertucci , Md Montaser Hamid , Yashwanthi Anand , Anita Ruangrotsakun , Delyar Tabatabai , Melissa Perez , and Minsuk Kahng
IEEE Transactions on Visualization and Computer Graphics (IEEE VIS 2022). Oklahoma City, OK
[4]

Mirror: Interactive Discovery of Blindspots in Machine Learning Models

Donald Bertucci , Alex Cabrera , Nari Johnson , Gregory Plumb , Erica Fu , and Adam Perer
An interactive tool to discover errors in machine learning models. Detailed in the poster and implemented in Zeno.
Human-Computer Interaction Institute (HCII) Summer Research Showcase (2022). Pittsburgh, PA
[3]

Beyond Value: CHECKLIST for Testing Inferences in Planning-Based Reinforcement Learning

Kin-Ho Lam , Delyar Tabatabai , Jed Irvine , Donald Bertucci , Anita Ruangrotsakun , Minsuk Kahng , and Alan Fern
32nd International Conference on Automated Planning and Scheduling (ICAPS 2022).
[2]

Backprop Explainer: Interactive Explanation of Backpropagation in Neural Network Training

Donald Bertucci and Minsuk Kahng
Workshop on Visualization for AI Explainability (VISxAI, IEEE VIS 2021).
[1]

An Interactive Introduction to Autoencoders

Donald Bertucci
Workshop on Visualization for AI Explainability (VISxAI, IEEE VIS 2021).

References

Dr. Minsuk Kahng

Senior Research Scientist at Google Deepmind, People + AI Research (PAIR)

Dr. Alex Cabrera

AI + Bio Startup, Founding Member of Technical Staff

Dr. Adam Perer

Professor at Carnegie Mellon University, Data Interaction Group

Dr. Dominik Moritz

Professor at Carnegie Mellon University, Data Interaction Group
Apple ML Research Scientist

Dr. Nathan Mortimer

Professor at Oregon State University, Venom Biochemistry and Molecular Biology Laboratory

Dr. Alex Endert

Professor at Georgia Institute of Technology, Visual Analytics Lab