Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete

Item #:

075280-1571

Details

DOI: https://doi.org/10.52202/075280-1571
Author(s): Daniel Bertschinger, Christoph Hertrich, Paul Jungeblut, Tillmann Miltzow, Simon Weber
Pages: 36222-36237 (16 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/075280-1571
Author(s): Daniel Bertschinger, Christoph Hertrich, Paul Jungeblut, Tillmann Miltzow, Simon Weber
Pages: 36222-36237 (16 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 36
Date/Location: Held 10-16 December 2023, New Orleans, Louisiana, USA.
Series: Advances in Neural Information Processing Systems 36
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)