… In this paper we propose a neuralnetwork training algorithm which converges to exactly this solution. We prove that the network converges from any initially random set of weights to …
S Becker - International Journal of Neural Systems, 1991 - World Scientific
… neuralnetworklearning algorithms which are related to Principal Components Analysis (PCA). These algorithms learn … could be learned in an unsupervisedneuralnetwork framework, …
… an unsupervised method to learn a neuralnetwork, namely an explainer, to interpret a pre-trained convolutional neuralnetwork … We also learn the explainer to use object-part features to …
… of neuralnetwork has been investigated in many studies [1–14]. This paper deals with an unsupervisedlearning … for the training of deep neuralnetworks. The conventional approach to …
… first step for a typical unsupervisedlearning technique is the estimation of these clusters. … We present here a new method for unsupervisedlearning in neuralnetworks (see also Atiya, …
W Pedrycz, J Waletzky - IEEE transactions on neural networks, 1997 - ieeexplore.ieee.org
… The essence of the approach introduced in this study is to construct a neuralnetwork that … (pattern) is transformed according to the nonlinear mapping realized by the neuralnetwork …
… in ordinary learning and conditioning. Self-organization has been a major preoccupation of those interested in neuralnetworks since the early days, and the volume edited by Yovits …
SD Fabiyi - International Journal of Computer Applications, 2019 - strathprints.strath.ac.uk
… of the unsupervisedlearning techniques … unsupervised artificial neuralnetworks algorithms including autoencoders and selforganizing maps. Unsupervised artificial neuralnetworks …
… learning input data item. For the purposes of clustering-based research, we focused on unsupervisedlearning … More specifically, we used Kohonen's learning rule and a variation on the …