Title :
Machine parts classification based on a digital neural network
Author :
Ouslim, M. ; Curtis, K.M.
Author_Institution :
Dept. of Electr. & Electron. Eng., Nottingham Univ., UK
Abstract :
This paper describes the application of a digital neural network, based on the probabilistic version of the RAM neuron (pRAM), to image processing. The most important pRAM controlling parameters are discussed, along with the application of two types of learning algorithm, based on reinforcement learning and data analysis. The performance of the system is evaluated with respect to its classification of machine parts within a black and white image
Keywords :
image classification; learning (artificial intelligence); neural nets; RAM neuron; controlling parameters; data analysis; digital neural network; image processing; learning algorithm; machine parts classification; pRAM; probabilistic version; reinforcement learning; Data analysis; Image processing; Image resolution; Learning; Neural networks; Neurons; Phase change random access memory; Random access memory; Read-write memory; Stochastic processes;
Conference_Titel :
Electronics, Circuits, and Systems, 1996. ICECS '96., Proceedings of the Third IEEE International Conference on
Conference_Location :
Rodos
Print_ISBN :
0-7803-3650-X
DOI :
10.1109/ICECS.1996.584444
