EURO-Online login
- New to EURO? Create an account
- I forgot my username and/or my password.
- Help with cookies
(important for IE8 users)
1774. Integrating Machine Learning with GAMSPy
Invited abstract in session TC-30: Modeling tools, stream Software for Optimization.
Tuesday, 12:30-14:00Room: 064 (building: 208)
Authors (first author is the speaker)
| 1. | Hamdi Burak Usul
|
Abstract
GAMSPy is a powerful mathematical optimization package which integrates Python's flexibility with GAMS's modeling performance. This combination opens doors to previously challenging applications, notably in bridging the worlds of machine learning (ML) and mathematical modeling. While GAMS excels in indexed algebra, ML predominantly relies on matrix operations. To enable applications in ML, our work introduces essential ML operations such as matrix multiplications, transpositions, and norms into GAMSPy. In this talk, we showcase the use of these additions by generating adversarial images for an optical character recognition network using GAMSPy. We highlight GAMSPy's versatility and its potential to be used in ML research and development. We delve into future prospects, show how GAMSPy's approach differs from existing alternatives and discuss innovative methods where mathematical modeling intersects with machine learning.
Keywords
- Mathematical Programming
- Machine Learning
- Software
Status: accepted
Back to the list of papers