Home » Posts tagged 'deep learning'
Tag Archives: deep learning
Except where otherwise noted, content on this site is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International license.
Tool demo paper on refactoring imperative DL programs to graph execution accepted at FASE ’25
Our paper entitled, “Hybridize functions: A tool for automatically refactoring imperative Deep Learning programs to graph execution,” has been accepted at the 2025 International Conference on Fundamental Approaches to Software Engineering (FASE) as a formal tool demonstration! Out of 31 papers (including 4 tool papers), 11 (including 1 tool paper) were accepted, amounting to a 35% acceptance rate. Congrats to Tatiana, Mehdi, Nan, and Anita!
Paper on reliably refactoring Deep Learning systems accepted at AISafety ’24
Our paper on reliability refactoring Deep Learning systems has been accepted to the 2024 AISafety workshop at the International Joint Conference on Artificial Intelligence (IJCAI ’24). Congratulations to Nan and Anita!
Preprint of ASE ’23 DL refactoring paper now available
A preprint of our ASE ’23 paper on refactoring imperative Deep Learning programs to graphs is now available.
Paper on refactoring imperative Deep Learning programs to graphs accepted at ASE ’23 NIER
Our paper entitled, “Towards Safe Automated Refactoring of Imperative Deep Learning Programs to Graph Execution” has been accepted to the New Ideas and Emerging Results (NIER) track at the IEEE/ACM 2023 International Conference on Automated Software Engineering (ASE)! Out of 70 papers, 25 were accepted, amounting to a 35.7% acceptance rate. The conference will take place later this year in Kirchberg, Luxembourg.
Congratulations to Tatiana, Mehdi, Nan, and Anita, and thank you for all of your hard work!
Talk at University of Tokyo
On August 18, I visited Professor Shigeru Chiba at the Core Software Group of the Dept. of Creative Informatics Graduate School of Information Science and Technology at The University of Tokyo. I gave a talk about preliminary research in automated refactoring of Deep Learning software.
(more…)“Migrating Imperative Deep Learning Programs to Graph Execution” guest lecture on YouTube
Thanks to Stevens Institute of Technology for posting my guest lecture on imperative Deep Learning program execution to YouTube!
Paper on hybridization challenges in imperative Deep Learning programs accepted at MSR ’22
Our paper entitled, “Challenges in migrating imperative Deep Learning programs to graph execution: An empirical study,” has been accepted to the main technical research track at the IEEE/ACM SIGSOFT 2022 International Conference on Mining Software Repositories (MSR)! Out of 138 papers, 45 were accepted, amounting to a 32.6% acceptance rate. The conference will take place later this year in Pittsburgh and is co-located with ICSE 2022.
A special congratulations to Tatiana for publishing her first full conference paper as first-author in the second year of her Ph.D. studies! Also congrats to Mehdi and Anita, and thank you for all of your hard work!
