Conclusions and future research

Eyal Kolman*, Michael Margaliot

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review


The ability of ANNs to learn and generalize from examples, and to generate robust solutions, makes them very suitable in a diversity of applications where algorithmic approaches are either unknown or difficult to implement. A major drawback, however, is that the knowledge learned by the network is represented in an exceedingly opaque form, namely, as a list of numerical coefficients. This black-box character of ANNs hinders the possibility of their more wide-spread acceptance. The problem of extracting the knowledge embedded in the ANN in a comprehensible form has been intensively addressed in the literature.

Original languageEnglish
Title of host publicationKnowledge-Based Neurocomputing
Subtitle of host publicationA Fuzzy Logic Approach
EditorsEyal Kolman, Michael Margaliot
PublisherSpringer Berlin Heidelberg
ISBN (Print)9783540880769
StatePublished - 2009

Publication series

NameStudies in Fuzziness and Soft Computing
ISSN (Print)1434-9922


Dive into the research topics of 'Conclusions and future research'. Together they form a unique fingerprint.

Cite this