In this paper, we provide a study on the learning adaptation of anunsupervised neural network when applied to machine part recognition.The network used is based on an unsupervised learning algorithm calledlearning by experience (LBE). Here, we modify the network so thatwhenever it encounters a memory full case, it adopts an approach byreleasing the constraint to counteract this effect. Hence, it providesthe flexibility for machine part recognition. Simulation results areincluded
展开▼