Greedy training algorithms for neural networks and applications to PDEs

Regularized Greedy Algorithms for Neural Network Training with Data Noise

The aim of this paper is to construct a modified greedy algorithm applicable for an ill-posed function approximation problem in presence of data noise. This algorithm, coupled with a suitable stopping rule, can be interpreted as an iterative regularization method. We provide a detailed convergence analysis of the algorithm in presence of noise, and discuss optimal choices of parameters. As a co...

Neural networks: Algorithms and applications

This special issue of Neurocomputing includes 24 original articles which are extended versions of selected papers from the Fourth International Symposium on Neural Networks (ISNN 2007). As a sequel to ISNN 2004/ISNN 2005/ISNN 2006, ISNN 2007 was held in June 2007, in Nanjing, China, an old capital of China and a modern metropolis with 2470year history. ISNN 2007 provided a high-level internatio...

Effective training algorithms for RBF-neural networks

New structure and training algorithms of the RBF-type neural network are proposed. An extra neuron layer is added to realize the principal component method. A novel training algorithm is designed for training each separate neuron in the hidden layer, which guarantees the efficiency and finiteness of the training procedure. Results were obtained for a variety of problems. In particular, the resu...

Introduction to Artificial Neural Networks Training and Applications

Analysis and Comparison of Algorithms for Training Recurrent Neural Networks

How did that work? No need to concern myself; the majority of people benefit from the technology of their civilization without understanding it.