Neural gas (NG) constitutes a very robust clustering algorithm which can be derived as stochastic gradient descent from a cost function closely connected to the quantization error...
Barbara Hammer, Alexander Hasenfuss, Thomas Villma...
This paper discusses the empirical evaluation of improving generalization performance of neural networks by systematic treatment of training and test failures. As a result of syst...
In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approx...
This study proposes a novel forecasting approach – an adaptive smoothing neural network (ASNN) – to predict foreign exchange rates. In this new model, adaptive smoothing techni...
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...