Neural network and genetic learning algorithms for computer-aided design and pattern recognition
Guardado en:
| Udgivet i: | ProQuest Dissertations and Theses (1992) |
|---|---|
| Hovedforfatter: | |
| Udgivet: |
ProQuest Dissertations & Theses
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
| Resumen: | Four different technologies, object-oriented programming, genetic algorithms, mathematical programming, and fuzzy set theory, have been employed for developing effective serial or concurrent neural network learning algorithms. First, a multi-layer neural network development environment (ANNDE) has been developed for implementing machine learning algorithms for the domain of engineering design using the object-oriented programming paradigm and implemented in C++ and G++ languages. An object-oriented momentum backpropagation learning algorithm has been implemented in ANNDE. Second, two concurrent backpropagation neural network learning algorithms have been developed employing the vectorization and microtasking capabilities of vector MIMD machines. The algorithms have been applied to two different domains: engineering design and image recognition. A maximum speedup of about 6.7 is achieved using eight processors for a large network with 5950 links due to microtasking only. Due to vectorization only, an average speedup of about 5.5 is achieved. Third, a new adaptive conjugate gradient neural network learning algorithm for training multi-layer feedforward neural network has been developed and implemented on a vector MIMD machine. The program of trial-and-error selection of learning and momentum ratios encountered in the momentum backpropagation learning algorithm is circumvented in the new adaptive learning algorithm. Due to microtasking only on a Cray Y-MP8/864 supercomputer, a maximum speedup of about 7.9 is achieved for a large network with 5950 links using eight processors. Four, a new concurrent hybrid genetic/neural network learning algorithm has been developed by integrating a genetic algorithm with the adaptive conjugate gradient neural network learning algorithm and implemented on a Cray Y-MP8/864 supercomputer. Finally, an unsupervised fuzzy neural network classification algorithm has been developed and applied to perform feature abstraction and classify a large number of training instances into a small number of clusters. A fuzzy neural network learning model has been developed by integrating the unsupervised fuzzy neural network classification algorithm with a genetic algorithm and an adaptive conjugate gradient neural network learning algorithm. The learning algorithm has been applied to the domain of image recognition. An average computational speedup of eight is achieved by the new algorithm. |
|---|---|
| ISBN: | 9798208256145 |
| Fuente: | ProQuest Dissertations & Theses Global |