Due to deep neural networks (DNNs) a large number of parameters, DNNs increase the demand for computing and storage during training, reasoning and deployment, especially when DNNs stack deeper and wider. Tensor decomposition can not only compress DNN models but also reduce parameters and storage requirements while maintaining high accuracy and performance. About tensor ring (TR) decomposition of tensor decomposition, there are two problems: (1) The practice of setting the TR rank to be equal in TR decomposition results in an unreasonable rank configuration. (2) The training time of selecting rank through iterative processes is time-consuming. To address the two problems, a TR network compression method by Variational Bayesian (TR-VB) is proposed based on the Global Analytic Solution of Empirical Variational Bayesian Matrix Factorization (GAS of EVBMF). The method consists of three steps: (1) rank selection, (2) TR decomposition, and (3) fine-tuning to recover accumulated loss of accuracy. Experimental results show that, for a given network, TR-VB gives the best results in terms of Top-1 accuracy, parameters, and training time under different compression levels. Furthermore, TR-VB validated on CIFAR-10/100 public benchmarks achieves state-of-the-art performance.
The problem of robust fault-tolerant control for a class of nonlinear networked control systems (NCSs) with parameter uncertainties is investigated in this paper. A T-S fuzzy model is employed to represent the nonlinear controlled plant in the NCSs. Both networked-induced delay and packet dropout in transmission are addressed. By using Lyapunov-Krasovskii functional, the less conservative integrity design for NCSs with failures of actuator and sensor is analyzed based on a delay-dependent approach, and the robust fault-tolerant controller gain can be obtained via solving several linear matrix inequalities (LMIs). Moreover, some slack matrices which reduce conservatism are introduced during the proof. Finally, an example is used to illustrate the effectiveness and the feasibility of the proposed approach.
Deep learning based image inpainting methods can synthesize plausible results based on known information of undamaged areas of the input image. However, most of the existing methods fail to generate high quality structures and textures due to a lack of fully exploring the potential high level semantic information of the generator. To address this issue, we first propose a novel Semantic-Wise Hybrid Attention Generative Adversarial Network (SWHA-GAN), which leverages a lightweight single-stream GAN framework to reconstruct reasonable and natural results. Secondly, a Semantic-Wise Hybrid Attention module is designed to simultaneously promote correct structure and rich details of the generated result. The channel self-attention emphasizes long range semantic dependencies among channels to improve structure accuracy, and spatial attention ensures texture inpainting. Experiments on multiple datasets including faces and natural images show that the proposed SWHA-GAN can generate higher quality results with more details than the state-of-the-arts.