Taming Binarized Neural Networks and Mixed-Integer Programs
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00379059" target="_blank" >RIV/68407700:21230/24:00379059 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1609/aaai.v38i10.28968" target="_blank" >https://doi.org/10.1609/aaai.v38i10.28968</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1609/aaai.v38i10.28968" target="_blank" >10.1609/aaai.v38i10.28968</a>
Alternative languages
Result language
angličtina
Original language name
Taming Binarized Neural Networks and Mixed-Integer Programs
Original language description
There has been a great deal of recent interest in binarized neural networks, especially because of their explainability. At the same time, automatic differentiation algorithms such as back-propagation fail for binarized neural networks, which limits their applicability. We show that binarized neural networks admit a tame representation by reformulating the problem of training binarized neural networks as a subadditive dual of a mixed-integer program, which we show to have nice properties. This makes it possible to use the framework of Bolte et al. for implicit differentiation, which offers the possibility for practical implementation of backpropagation in the context of binarized neural networks. This approach could also be used for a broader class of mixed-integer programs, beyond the training of binarized neural networks, as encountered in symbolic approaches to AI and beyond.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
R - Projekt Ramcoveho programu EK
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 38th AAAI Conference on Artificial Intelligence
ISBN
—
ISSN
2159-5399
e-ISSN
2374-3468
Number of pages
9
Pages from-to
10935-10943
Publisher name
AAAI Press
Place of publication
Menlo Park
Event location
Vancouver
Event date
Feb 20, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001241513600021