DocumentCode :
1622052
Title :
A quantitative study of experimental neural network learning algorithm evaluation practices
Author :
Prechelt, L.
Author_Institution :
Karlsruhe Univ., Germany
fYear :
1995
Firstpage :
223
Lastpage :
227
Abstract :
113 articles about neural network learning algorithms published in 1993 and 1994 are examined for the amount of experimental evaluation they contain. Every third of them does employ not even a single realistic or real learning problem. Only 6% of all articles present results for more than one problem using real world data. Furthermore, one third of all articles does not present any quantitative comparison with a previously known algorithm. These results indicate that the quality of research in the area of neural network learning algorithms needs improvement. The publication standards should be raised and easily accessible collections of example problems be built
Keywords :
learning (artificial intelligence); neural nets; reviews; experimental evaluation; experimental neural network learning algorithm evaluation practices; quantitative study; real world data;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Artificial Neural Networks, 1995., Fourth International Conference on
Conference_Location :
Cambridge
Print_ISBN :
0-85296-641-5
Type :
conf
DOI :
10.1049/cp:19950558
Filename :
497820
Link To Document :
بازگشت