Appears in The Intl Symposium on Integrating Knowledge and Neural Heuristics ( ISIKNH - 94 )
نویسنده
چکیده
This paper describes Rapture | a system for revising probabilistic rule bases that converts symbolic rules into a connectionist network, which is then trained via connectionist techniques. It uses a modiied version of backpropagation to reene the certainty factors of the rule base, and uses ID3's information-gain heuristic (Quinlan, 1986) to add new rules. Work is currently under way for nding improved techniques for modifying network architectures that include adding hidden units using the UPSTART algorithm (Frean, 1990). A case is made via comparison with fully connected connectionist techniques for keeping the rule base as close to the original as possible, adding new input units only as needed.
منابع مشابه
The Intl Symposium on Integrating Knowledge and Neural
This paper describes Rapture | a system for revising probabilistic rule bases that converts symbolic rules into a connectionist network, which is then trained via connectionist techniques. It uses a modi ed version of backpropagation to re ne the certainty factors of the rule base, and uses ID3's information-gain heuristic (Quinlan, 1986) to add new rules. Work is currently under way for nding ...
متن کاملIntegration of Knowledge and Neural Heuristics
In his keynote speech, B. Chandrasekaran (The Ohio State University) argued that the debate about the right approach to AI could be clarified by removing many confusing notions with regard to what made something a representation. In one case, content is more important than form, whereas in the other, the reverse is true. He pointed out that proper understanding of Alan Newell’s knowledge level ...
متن کاملThe 17th congress of parenteral and enteral Nutrition society of Asia (PENSA) and the first symposium on fasting and health, 6th-8th December 2016, Tehran, Iran
The 17th Congress of Parenteral and Enteral Nutrition Society of Asia (PENSA 2016) and the first Symposium on Fasting and Health will be held on 6th to 8th December 2016 at Olympic Hotel, Tehran, Iran. The congress is hosted by Tehran University of Medical Sciences, Semnan University of Medical Sciences and Scientific Committee of Iranian Nutrition Society. This congress is organized with the p...
متن کاملPrediction of Surface Roughness by Hybrid Artificial Neural Network and Evolutionary Algorithms in End Milling
Machining processes such as end milling are the main steps of production which have major effect on the quality and cost of products. Surface roughness is one of the considerable factors that production managers tend to implement in their decisions. In this study, an artificial neural network is proposed to minimize the surface roughness by tuning the conditions of machining process such as cut...
متن کاملNeural Network Based Recognition System Integrating Feature Extraction and Classification for English Handwritten
Handwriting recognition has been one of the active and challenging research areas in the field of image processing and pattern recognition. It has numerous applications that includes, reading aid for blind, bank cheques and conversion of any hand written document into structural text form. Neural Network (NN) with its inherent learning ability offers promising solutions for handwritten characte...
متن کامل