Slides from my talk at George Mason University (GMU) on “Challenges in Migrating Imperative Deep Learning Programs to Graph Execution: An Empirical Study” are now available.
Pages
Recent News
- Tatiana presenting on DL refactoring at ASE ’23
- Slides for ASE ’23 NIER paper on imperative Deep Learning refactoring now available
- Preprint of ASE ’23 DL refactoring paper now available
- Tatiana to present at the ASE 2023 doctoral forum
- 2023 NYU GSTEM students visit during the summer
- Paper on refactoring imperative Deep Learning programs to graphs accepted at ASE ’23 NIER
- New doctoral student Benjamin Prud’homme starts Fall 2023
- Paper on actor mutation testing accepted at ESE/FSE ’23
- Program Committee (PC) member for ESEC/FSE ’23 demonstrations
- Program Committee (PC) member for ICSME ’23 doctoral symposium
Subscribe
Archives
Categories
Tags
2022
2023
ase
aspect-oriented programming
automated refactoring
automatic parallelization
award
computer science
conference
cuny
deep learning
default methods
eclipse
empirical software engineering
empirical study
esec/fse
grant
grants
icse
ieee
java
java 8
new paper
new student
new york city
nsf
office hours
plugin
poster
preprint
program committee member
programming languages
refactoring
research
reviewer
slides
software engineering
splash
streams
students
summer research
talk
tool demonstrations
travel
workshop
Except where otherwise noted, content on this site is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.
Slides from GMU talk about challenges in executing imperative Deep Learning programs as graphs
Tags: deep learning, GMU, imperative programming, slides
← “Migrating Imperative Deep Learning Programs to Graph Execution” guest lecture on YouTube Student mentor at ICSE ’22 →
