math + software


SELECTED RESEARCH

Grounding inductive biases in natural images

invariance in deep learning stems from variations in data, NeurIPS 2021.

> paper + code

Diane Bouchacourt, Mark Ibrahim, Ari S. Morcos


Building AI that can understand variation in the world around us

Addressing the Topological Defects of Disentanglement via Distributed Operators, 2021

> paper + code + blog post

Diane Bouchacourt, Mark Ibrahim, Stéphane Deny


Global Explanations for Neural Networks

Mapping the Landscape of Predictions, ACM AAAI 2019

> paper + open source library + blog post

Mark Ibrahim, Melissa Louie, Ceena Modarres, John Paisley (Columbia University)


Mixed Membership Recurrent Neural Networks

Modeling varying time intervals and group dynamics, ACM International Conference on AI in Finance 2021

> paper

Ghazal Fazelnia, Mark Ibrahim, Ceena Modarres, Kevin Wu, John Paisley


Influence in Directed Cyclic Graphs

Connecting Every Bit of Knowledge: Wikipedia's First Link Network. 2017, Journal of Computational Science.

Mark Ibrahim, Christoper Danforth, Peter Dodds (U. Vermont Mathematics Department)



Neural Networks

my notes on what they are and how they learn

Knowledge Network

a graph-based knowledge search engine powered by Wikipedia

connect ideas

Talks


Georgia Tech's Deep Learning Course Instructor (2022)
Lecture on "Feed Forward Neural Networks"

PyCon US 2020 (Python Conference)
Talk on "Machine Learning on Encrypted Data with CrypTen"

NeurIPS 2018 FEAP Workshop Spotlight Talk (Dec 2018)
"Towards Explainable Deep Learning for Credit Lending"

New York Python Meetup (Dec 2018)
Data Science Talk: " Explaining Deep Learning Models"

Applied Machine Learning Tom Tom Conference (April 2018)
"Explainable AI: Key Techniques and Societal Implications"

George Washington University, Data Driven Conference (Dec 2017)
"Understanding the Predictions of Deep Neural Networks"

NYC Data Wranglers Meetup (Aug 2016)
Data Science in Practice: "Building a Graph-Based Search Engine"


Courses Taught at the University of Vermont


Calculus I 71 eager minds,

Calculus II 38 étudiants, and

College Algebra 42 estudiantes.