@inbook{ea6912842a8841e7bec08de7ca79b8f8,
title = "Conclusions and future research",
abstract = "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.",
author = "Eyal Kolman and Michael Margaliot",
year = "2009",
doi = "10.1007/978-3-540-88077-6_7",
language = "אנגלית",
isbn = "9783540880769",
series = "Studies in Fuzziness and Soft Computing",
publisher = "Springer Berlin Heidelberg",
pages = "77--81+89--98",
editor = "Eyal Kolman and Michael Margaliot",
booktitle = "Knowledge-Based Neurocomputing",
}