Autonomous self-configuration of artificial neural networks for data classification or system control

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Artificial neural networks (ANNs) are powerful methods for the classification of multi-dimensional data as well as for the control of dynamic systems. In general terms, ANNs consist of neurons that are, e.g., arranged in layers and interconnected by real-valued or binary neural couplings or weights. ANNs try mimicking the processing taking place in biological brains. The classification and generalization capabilities of ANNs are given by the interconnection architecture and the coupling strengths. To perform a certain classification or control task with a particular ANN architecture (i.e., number of neurons, number of layers, etc.), the inter-neuron couplings and their accordant coupling strengths must be determined (1) either by a priori design (i.e., manually) or (2) using training algorithms such as error back-propagation. The more complex the classification or control task, the less obvious it is how to determine an a priori design of an ANN, and, as a consequence, the architecture choice becomes somewhat arbitrary. Furthermore, rather than being able to determine for a given architecture directly the corresponding coupling strengths necessary to perform the classification or control task, these have to be obtained/learned through training of the ANN on test data. We report on the use of a Stochastic Optimization Framework (SOF; Fink, SPIE 2008) for the autonomous self-configuration of Artificial Neural Networks (i.e., the determination of number of hidden layers, number of neurons per hidden layer, interconnections between neurons, and respective coupling strengths) for performing classification or control tasks. This may provide an approach towards cognizant and self-adapting computing architectures and systems

Original languageEnglish (US)
Title of host publicationSpace Exploration Technologies II
DOIs
StatePublished - Sep 14 2009
EventSpace Exploration Technologies II - Orlando, FL, United States
Duration: Apr 13 2009Apr 13 2009

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7331
ISSN (Print)0277-786X

Other

OtherSpace Exploration Technologies II
CountryUnited States
CityOrlando, FL
Period4/13/094/13/09

Keywords

  • Artificial neural networks
  • Autonomous self-configuration
  • Coupling strengths
  • Data classification
  • Network architecture
  • Neural couplings
  • Neurons
  • Robustness
  • Simulated annealing
  • Stochastic optimization framework
  • System control
  • Training

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Autonomous self-configuration of artificial neural networks for data classification or system control'. Together they form a unique fingerprint.

  • Cite this

    Fink, W. (2009). Autonomous self-configuration of artificial neural networks for data classification or system control. In Space Exploration Technologies II [733105] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7331). https://doi.org/10.1117/12.821836