Laboratorio Cini Data Science

The Department of Engineering, Università degli Studi di Perugia organizes the seminar entitled Training Fully Connected Neural Networks is ∃R-Complete. The seminar is taught by Paul Jungeblut of Karlsruhe Institute of Technology (KIT).

Abstract: 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.

The seminar is taught within the PhD course in Industrial and information engineering.

News by prof. Fabrizio Montecchiani, Department of Engineering, Università degli Studi di Perugia.