The Spiral Discovery Network as an Automated General-Purpose Optimization Tool

Complexity 2018:1-8 (2018)
  Copy   BIBTEX

Abstract

The Spiral Discovery Method was originally proposed as a cognitive artifact for dealing with black-box models that are dependent on multiple inputs with nonlinear and/or multiplicative interaction effects. Besides directly helping to identify functional patterns in such systems, SDM also simplifies their control through its characteristic spiral structure. In this paper, a neural network-based formulation of SDM is proposed together with a set of automatic update rules that makes it suitable for both semiautomated and automated forms of optimization. The behavior of the generalized SDM model, referred to as the Spiral Discovery Network, and its applicability to nondifferentiable nonconvex optimization problems are elucidated through simulation. Based on the simulation, the case is made that its applicability would be worth investigating in all areas where the default approach of gradient-based backpropagation is used today.

Other Versions

No versions found

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 103,449

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Analysis on GenAI for Source Code Scanning and Automated Software Testing.Girish Wali Praveen Sivathapandi - 2025 - International Journal of Multidisciplinary Research in Science, Engineering and Technology 8 (2):631-638.

Analytics

Added to PP
2018-03-13

Downloads
14 (#1,321,670)

6 months
2 (#1,294,541)

Historical graph of downloads
How can I increase my downloads?

Citations of this work

No citations found.

Add more citations

References found in this work

No references found.

Add more references