Il Dipartimento di Ingegneria, Università degli Studi di Perugia organizza il seminario dal titolo Training Fully Connected Neural Networks is ∃R-Complete. Il seminario è tenuto da Paul Jungeblut, Karlsruhe Institute of Technology (KIT).
Abstract del seminario: we consider the algorithmic complexity of training fully connected neural networks. In particular, we see that this problem is ER-complete. This means that it is (up to polynomial transformations) equally difficult as finding the solutions of a system of polynomial equations and inequalities in several unknowns.
In the talk I will introduce the neural network training problem and give some background on ER-completeness. Then we combine both to get an idea how ER-completeness is proven.
The talk is based on our recent paper available at https://arxiv.org/abs/2204.01368.
Il seminario è tenuto all'interno del corso di dottorato in Ingegneria industriale e dell'informazione.
News by prof. Fabrizio Montecchiani, Dipartimento di Ingegneria, Università degli Studi di Perugia.
Cini Lab on Data Science
Special Sessions on Big Data at CLADAG 2015
Pula (Cagliari), 8th-10th October 2015: the Lab organizes th ...
Data Public-Private Partnership
The Data Public Private Partnership aims at strengthening th ...
Governments should embrace Big Data
Commission urges governments to embrace potential of Big Dat ...
-
Seminar: Software Engineering Abstractions for Metaheuristics: a 20 years journey
09-01-2023 21:51:27
The research group Complex Intelligent Systems (CIS) of the Department of Mathematics and Computer...
-
SoBigData.it: Italian Research Infrastructure
21-12-2022 22:09:58
The SoBigData Research Infrastructure (RI) is a distributed, multidisciplinary research...
-
Ernesto Damiani participating to UNESCO Global Conference on Universal Access to Information 2022
26-09-2022 09:13:43
Prof. Ernesto Damiani, president of CINI, has been invited to the Global Conference on Universal...