A new learning strategy is proposed for training of radial basis functions (RBF) network. We apply two different local optimization methods to update the output weights in training process, the gradient method and a combination of the gradient and Newton methods. Numerical results obtained in solving nonlinear integral equations show the excellent performance of the combined gradient method in ...

In this paper we calculate the gradient of the energy function in XMVB software through the technique of automatic differentiation, instead of finite difference method. To reduce the memory requirement of the adjoint model, the hierarchical trajectory method is used. The results show that the time cost for calculating gradients, as well as for running the total XMVB, is dramatically cut down by...

The degradation rate of Mediterranean steppes, especially in North Africa is 1% per year, and this considered a high  rate of degradation. This study conducted in 2014 in the south slope of the Al-Jabal Al-Akhdar, northeast Libya to quantify the vegetation recovery rate and assess selected Vegetation Indices (VIs) for mapping rangelands degradation status using remote sensing technology. Throug...

The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD(λ) to data efficient least squares methods. Least square methods make the best use of available data directly computing the TD solution and thus do not require tuning a typically highly sensitive learning rate parameter, but require quadratic computation and storage. Recent algorith...