Showing papers on "Hybrid neural network published in 1990"

Hybrid neural network and rule-based pattern recognition system capable of self-modification

Abstract: This paper describes a hybrid neural network and rule-based pattern recognition system architecture which is capable of self-modification or learning. The central research issue to be addressed for a multiclassifier hybrid system is whether such a system can perform better than the two classifiers taken by themselves. The hybrid system employs a hierarchical architecture, and it can be interfaced with one or more sensors. Feature extraction routines operating on raw sensor data produce feature vectors which serve as inputs to neural network classifiers at the next level in the hierarchy. These low-level neural networks are trained to provide further discrimination of the sensor data. A set of feature vectors is formed from a concatenation of information from the feature extraction routines and the low-level neural network results. A rule-based classifier system uses this feature set to determine if certain expected environmental states, conditions, or objects are present in the sensors' current data stream. The rule-based system has been given an a priori set of models of the expected environmental states, conditions, or objects which it is expected to identify. The rule-based system forms many candidate directed graphs of various combinations of incoming features vectors, and it uses a suitably chosenmore » metric to measure the similarity between candidate and model directed graphs. The rule-based system must decide if there is a match between one of the candidate graphs and a model graph. If a match is found, then the rule-based system invokes a routine to create and train a new high-level neural network from the appropriate feature vector data to recognize when this model state is present in future sensor data streams. 12 refs., 3 figs.« less

Information retrieval using hybrid multi-layer neural networks

Abstract: A hierarchical hybrid neural network comprising simple neural networks provided significantly higher accuracy in data retrieval that single neural network architectures. Both approaches were applied to information retrieval from large databases using textual retrieval keys where either the retrieval key or the data in the database are noisy. The results were improved by using different network training methods for highly correlated and less correlated data. The combination of self-organizing and supervised learning neural networks solved this problem, providing a retrieval accuracy of 93% when presented with noisy data, providing a fast training time, and allowing the solution to be scaled up

Hybrid neural network and pattern classification learning algorithms

Abstract: Some key research issues in learning for feedforward networks are addressed. Some results from learning from examples are discussed, and how this relates to learning in networks is pointed out. Some limitations of algorithms and alternative strategies that involve changing network architectures or input data transformations are discussed. An example of how a self-organizing feature map can be used in conjunction with a feedforward network to achieve good results in isolated word recognition is given. >