Constructing the basis path set by eliminating the path dependency

DOI10.1007/S11424-022-0208-7zbMATH Open1502.68249arXiv2007.00657OpenAlexW3039745655WikidataQ114222440 ScholiaQ114222440MaRDI QIDQ2109299FDOQ2109299

Authors: Yanyan Li 

Publication date: 20 December 2022

Published in: Journal of Systems Science and Complexity (Search for Journal in Brave)

Abstract: The way the basis path set works in neural network remains mysterious, and the generalization of newly appeared G-SGD algorithm to more practical network is hindered. The Basis Path Set Searching problem is formulated from the perspective of graph theory, to find the basis path set in a regular complicated neural network. Our paper aims to discover the underlying cause of path dependency between two independent substructures. Algorithm DEAH is designed to solve the Basis Path Set Searching problem by eliminating such path dependency. The path subdivision chain is proposed to effectively eliminate the path dependency inside the chain and between chains. The theoretical proofs and analysis of polynomial time complexity are presented. The paper therefore provides one methodology to find the basis path set in a more general neural network, which offers theoretical and algorithmic support for the application of G-SGD algorithm in more practical scenarios.

Full work available at URL: https://arxiv.org/abs/2007.00657

Recommendations

• Interpreting the basis path set in neural networks
• The basis suppression method
• scientific article; zbMATH DE number 4189228
• scientific article; zbMATH DE number 1753154
• Fast, efficient and accurate solutions to the Hamiltonian path problem using neural approaches

zbMATH Keywords

neural networkpath dependencybasis pathpath subdivision chainsubstructure path

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Graph theory (including graph drawing) in computer science (68R10) Paths and cycles (05C38)

Cites Work

• Learning representations by back-propagating errors
• Combinatorial optimization. Theory and algorithms.
• Digraphs
• Edge subdivision and edge multisubdivision versus some domination related parameters in generalized corona graphs
• Title not available (Why is that?)
• Arc Routing
• A game-based approximate verification of deep neural networks with provable guarantees
• Subdivisions of graphs: A generalization of paths and cycles
• Stability and Hopf bifurcation analysis of an \((n+m)\)-neuron double-ring neural network model with multiple time delays
• The complexity of explaining neural networks through (group) invariants

Cited In (1)

• Interpreting the basis path set in neural networks

This page was built for publication: Constructing the basis path set by eliminating the path dependency

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2109299)