Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks

Authors: Matthew Farrugia-Roberts

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we study functional equivalence classes for single-hidden-layer networks with the hyperbolic tangent nonlinearity, building on the foundational work of Sussmann (1992) on reducibility in this setting. We offer the following theoretical contributions.
Researcher Affiliation Academia Matthew Farrugia-Roberts School of Computing and Information Systems The University of Melbourne matthew@far.in.net
Pseudocode Yes Algorithm 4.1 (Parameter canonicalisation). Given a parameter space Wh, proceed:
Open Source Code No The paper does not contain any statement about releasing source code or provide a link to a code repository for the methodology described.
Open Datasets No The paper is purely theoretical and does not describe any experiments involving datasets, training, or public data availability.
Dataset Splits No The paper is theoretical and does not describe any experimental setup with dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any experiments that would require hardware specifications.
Software Dependencies No The paper is theoretical and does not describe any computational implementation or experiments requiring specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include details on experimental setup, hyperparameters, or training configurations.