Connectionist expert system with adaptive learning capability
نویسندگان
چکیده
منابع مشابه
A connectionist expert system for fault diagnosis
The design of a connectionist expert system for the fault diagnosis of a distribution system is proposed. The heuristic rules acquired from distribution dispatchers' experiences are incorporated into the connectionist network which can be utilized as the expert system knowledge base. The data sets used to train the connectionist network are the current waveforms recorded upon the occurrence of ...
متن کاملA Connectionist Expert System that Actually Works
The Space Environment Laboratory in Boulder has collaborated with the University of Colorado to construct a small expert system for solar flare forecasting, called THEa. It performed as well as a skilled human forecaster. We have constructed TheoNet, a three-layer back-propagation connectionist network that learns to forecast flares as well as THEa does. TheoNet's success suggests that a connec...
متن کاملConnectionist Learning Classifier System
Impetuous development of artificial neural networks makes it possible to transfer many ideas from this area into adjacent areas. This work investigates an opportunity of mapping learning classifier systems (LCS) into artificial neural networks (ANN). Possible learning types for hybrid connectionist classifier system (CLCS) for multi-step problems are derived. Transformation’s opportunity of the...
متن کاملA simulating cognitive system with adaptive capability.
Dedicated to the memory of Michael Conrad, this paper builds on his seminal ideas expressed in his famous book Adaptability, as well as in his later works. We investigate a recently published adaptive system for the instantaneous recognition of dynamics with respect to its adaptability to the Lorenz system. The system consists of a pool of internal dynamical elements. These elements are defined...
متن کاملA Connectionist Expert Approach
Artificial Neural Networks (ANNs) are widely and successfully used in speech recognition, but still many limitations are inherited to their topologies and learning style. In an attempt to overcome these limitations, we combine in a speech recognition hybrid system the pattern processing of ANNs and the logical inferencing of symbolic approaches. In particular, we are interested in the Connectio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Knowledge and Data Engineering
سال: 1991
ISSN: 1041-4347
DOI: 10.1109/69.88000