caa a22 4500 477073034 CHVBK 20180405111431.0 cr unu---uuuuu 170330e19960601xx s 000 0 eng 10.1007/BF01413743 doi (NATIONALLICENCE)springer-10.1007/BF01413743 Vaughn Marilyn Computing Information Systems Management Group, Cranfield University, RMCS, SN6 8LA, Shrivenham, Swindon, UK aut Interpretation and knowledge discovery from the multilayer perceptron network: Opening the black box [Elektronische Daten] [Marilyn Vaughn] This paper interprets the outputs from the multilayer perceptron (MLP) network by finding the input data features at the input layer of the network which activate the hidden layer feature detectors. This leads directly to the deduction of the significant data inputs, the inputs that the network actually uses to perform the input/output mapping for a classification task, and the discovery of the most significant of these data inputs. The analysis presents a method for providing explanations for the network outputs and for representing the knowledge learned by the network in the form of significant input data relationships. During network development the explanation facilities and data relationships can be used for network validation and verification, and after development, for rule induction and data mining where this method provides a potential tool for knowledge discovery in databases (KDD). Springer-Verlag London Limited, 1996 Data mining nationallicence Explanation facilities nationallicence Interpretation nationallicence Knowledge discovery nationallicence Rule induction nationallicence Validation and verification nationallicence Neural Computing & Applications Springer-Verlag 4/2(1996-06-01), 72-82 0941-0643 4:2<72 1996 4 521 https://doi.org/10.1007/BF01413743 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF01413743 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Vaughn Marilyn Computing Information Systems Management Group, Cranfield University, RMCS, SN6 8LA, Shrivenham, Swindon, UK aut NATIONALLICENCE 773 0- Neural Computing & Applications Springer-Verlag 4/2(1996-06-01), 72-82 0941-0643 4:2<72 1996 4 521 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer