Automatic Acquisition of Symbolic Knowledge from Subsymbolic Neural Networks
نویسندگان
چکیده
Knowledge acquisition is a bottleneck in AI applications. Neural learning is a new perspective in knowledge acquisition. In our approach we have extended Kohonen's self-organizing feature maps (SOFM) by the U-matrix method for the discovery of structures resp. classes. We have developed a machine learning algorithm, called SIG*, which automated extracts rules out of SOFM which are trained to classify high-dimensional data. SIG* selects significant attributes and constructs appropriate conditions for them in order to characterize each class. And SIG* generates also differentiating rules, which distinguish classes from each other. The algorithm has been tested on many different data sets with promising results. The framework of using SIG* integrated in a system which automated acquires knowledge from learned SOFM is also presented. An additional approach to extract fuzzy rules out of a SOFM will be developed
منابع مشابه
of the Nonconscious Acquisition A Symbolic Model
This article presents counter evidence against Smolensky’s theory thot human intuitive/nonconscious congnitive processes can only be accurately explained in terms of subsymbolic computations carried out in artificial neural networks. We present symbolic learning models of two well-studied, complicated cognitive tasks involving nonconscious acquisition of information: learning production rules a...
متن کاملBeyond Simple Rule Extraction: Acquiring Planning Knowledge from Neural Networks
This paper discusses learning in hybrid models that goes beyond simple classification rule extraction from backpropagation networks. Although simple rule extraction has received a lot of research attention, we need to further develop hybrid learning models that learn autonomously and acquire both symbolic and subsymbolic knowledge. It is also necessary to study autonomous learning of both subsy...
متن کاملA Symbolic Model of the Nonconscious Acquisition of Information
The paper presents counter evidence against Smolensky's theory that human in-tuitive/nonconscious cognitive processes can only be accurately explained in terms of subsymbolic computations carried out in artiicial neural networks. We present symbolic learning models of two well studied, complicated cognitive tasks involving nonconscious acquisition of information: learning production rules and a...
متن کاملKnowledge Extraction from Artificial Neural Networks and Applications
Knowledge acquisition is a frequent bottleneck in artificial intelligence applications. Neural learning may offer a new perspective in this field. Using Self-Organising Neural Networks, as the Kohonen model, the inherent structures in high-dimensional input spaces are projected on a low dimensional space. The exploration of structures resp. classes is then possible applying the U-Matrix method ...
متن کاملA symbolic/subsymbolic interface protocol for cognitive modeling
Researchers studying complex cognition have grown increasingly interested in mapping symbolic cognitive architectures onto subsymbolic brain models. Such a mapping seems essential for understanding cognition under all but the most extreme viewpoints (namely, that cognition consists exclusively of digitally implemented rules; or instead, involves no rules whatsoever). Making this mapping reduces...
متن کامل