Local Identifiability of Deep ReLU Neural Networks: the Theory

Authors: Joachim Bona-Pellissier, François Malgouyres, Francois Bachoc

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We did not run experiments.
Researcher Affiliation Academia Institut de Mathématiques de Toulouse ; UMR 5219 Université de Toulouse ; CNRS a UT1, F-31042 Toulouse, France b UPS, F-31062 Toulouse Cedex 9, France
Pseudocode No The paper provides mathematical derivations and theorems but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper states, 'We did not run experiments.', indicating no source code for a methodology to be released.
Open Datasets No The paper explicitly states, 'We did not run experiments.', therefore no datasets are used for training.
Dataset Splits No The paper explicitly states, 'We did not run experiments.', therefore no validation sets or splits are mentioned.
Hardware Specification No The paper explicitly states, 'We did not run experiments.', therefore no hardware specifications are provided.
Software Dependencies No The paper explicitly states, 'We did not run experiments.', therefore no software dependencies with version numbers are provided.
Experiment Setup No The paper explicitly states, 'We did not run experiments.', therefore no specific experimental setup details like hyperparameters or training configurations are provided.