Sciweavers

243 search results - page 3 / 49
» Interpretation of Trained Neural Networks by Rule Extraction
Sort
View
ICANN
2007
Springer
15 years 3 months ago
Generalized Softmax Networks for Non-linear Component Extraction
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Jörg Lücke, Maneesh Sahani
119
Voted
ESANN
1997
14 years 11 months ago
Extraction of crisp logical rules using constrained backpropagation networks
Two recently developed methods for extraction of crisp logical rules from neural networks trained with backpropagation algorithm are compared. Both methods impose constraints on th...
Wlodzislaw Duch, Rafal Adamczak, Krzysztof Grabcze...
CIBCB
2005
IEEE
14 years 11 months ago
Neuro-fuzzy Prediction of Biological Activity and Rule Extraction for HIV-1 Protease Inhibitors
— A fuzzy neural network (FNN) and multiple linear regression (MLR) were used to predict biological activities of 26 newly designed HIV-1 protease potential inhibitory compounds....
Razvan Andonie, Levente Fabry-Asztalos, Catharine ...
84
Voted
VLDB
1995
ACM
181views Database» more  VLDB 1995»
15 years 1 months ago
NeuroRule: A Connectionist Approach to Data Mining
Classification, which involves finding rules that partition a given da.ta set into disjoint groups, is one class of data mining problems. Approaches proposed so far for mining cla...
Hongjun Lu, Rudy Setiono, Huan Liu
IEEEICCI
2002
IEEE
15 years 2 months ago
Quasi-Morphism and Comprehensibility of Rules in Inductive Learning
We present a model of creating a hierarchical set of rules that encode generalizations and exceptions derived from induction learning. The rules use the input features directly an...
Wiphada Wettayaprasit, Chidchanok Lursinsap, Chee-...