This article presents an electromagnetic inversion algorithm for the design of cascaded metasurfaces that enables process to begin from more practical output field specifications, such as a desired power pattern or far-field (FF) performance criteria. Thus, this method combines greater transformation support multiple with flexibility inverse source framework. To end, two optimization problems a...

High cost of training time caused by multi-step adversarial example generation is a major challenge in training. Previous methods try to reduce the computational burden using single-step schemes, which can effectively improve efficiency but also introduce problem “catastrophic overfitting”, where robust accuracy against Fast Gradient Sign Method (FGSM) achieve nearby 100% whereas Projected Desc...

Variational models with second order regularizers can efficiently overcome the problems of staircasing effects caused by first models. However, different types may lead to properties feature preserving in restored images. In this paper, we show two variational regularizers. The one is bounded Hessian model Jacobian normals, which uses image intensity normals as regularizer, it an extension clas...

Image style transfer (IST) has drawn broad attention recently. At present, convolutional neural network (CNN)-based methods and generative adversarial (GAN)-based have been broadly utilized in IST. However, the texture of images obtained by most presents a lower definition, which leads to insufficient details To this end, authors present new IST method based on an enhanced GAN with prior circul...

We investigate the learning rate of multiple kernel leaning (MKL) with l1 and elastic-net regularizations. The elastic-net regularization is a composition of an l1-regularizer for inducing the sparsity and an l2-regularizer for controlling the smoothness. We focus on a sparse setting where the total number of kernels is large but the number of non-zero components of the ground truth is relative...

In this paper, we investigate the total variation diminishing property for a class of 2-stage explicit Rung-Kutta methods of order two (RK2) when applied to the numerical solution of special nonlinear initial value problems (IVPs) for (ODEs). Schemes preserving the essential physical property of diminishing total variation are of great importance in practice. Such schemes are free of spurious o...