Search

The principle of electroless copper plating technology and its application status and production process in through-hole metallization, inner copper foil treatment, electronic packaging technology and electromagnetic wave shielding in printed circuit board (PCB) are briefly introduced. The development of electroless copper plating in microelectronics is prospected.

We present an integrated metro-access networking scheme based on Alamouti-coded multi-carrier modulation and simplified sub-band coherent detection, and experimentally demonstrated it with real-time DSP in a 300-km communication link carrying live VR traffic, showing error-free performance with a low end-to-end latency of 1.5 ms.

This paper proposes a novel common-mode voltage (CMV) elimination (CMV-EL) method based on model predictive control (MPC) to eliminate CMV for three-level T-type inverters (3LT2Is). In the proposed MPC method, only six medium and one zero voltage vectors (VVs) (6MV1Z) that generate zero CMV are considered as candidates to perform the MPC. Moreover, the influence of dead-time effects on the CMV of the MPC-based 6MV1Z method is investigated, and the candidate VVs are redesigned by pre-excluding the VVs that will cause CMV fluctuations during the dead time from 6MV1Z. Only three or five VVs are included to perform optimization in every control period, which can significantly reduce the computational complexity. Thus, a small control period can be implemented in the practical applications to achieve improved grid current performance. With the proposed CMV-EL method, the CMV of the 3LT2Is can be effectively eliminated. In addition, the proposed CMV-EL method can balance the neutral point potentials (NPPs) and yield satisfactory performance for grid current tracking in steady and dynamic states. Simulation and experimental results are presented to verify the effectiveness of the proposed method.

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods have a strong bias towards low- or high-order interactions, or rely on expertise feature engineering. In this paper, we show that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions. The proposed framework, DeepFM, combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture. Compared to the latest Wide & Deep model from Google, DeepFM has a shared raw feature input to both its "wide" and "deep" components, with no need of feature engineering besides raw features. DeepFM, as a general learning framework, can incorporate various network architectures in its deep component. In this paper, we study two instances of DeepFM where its "deep" component is DNN and PNN respectively, for which we denote as DeepFM-D and DeepFM-P. Comprehensive experiments are conducted to demonstrate the effectiveness of DeepFM-D and DeepFM-P over the existing models for CTR prediction, on both benchmark data and commercial data. We conduct online A/B test in Huawei App Market, which reveals that DeepFM-D leads to more than 10% improvement of click-through rate in the production environment, compared to a well-engineered LR model. We also covered related practice in deploying our framework in Huawei App Market., Comment: 14 pages. arXiv admin note: text overlap with arXiv:1703.04247

A novel strategy based on a zero common mode voltage pulse-width modulation (ZCMV-PWM) technique and zero-sequence circulating current (ZSCC) feedback control is proposed in this study to eliminate ZSCCs between three-level neutral point clamped (NPC) voltage source inverters, with common AC and DC buses, that are operating in parallel. First, an equivalent model of ZSCC in a three-phase three-level NPC inverter paralleled system is developed. Second, on the basis of the analysis of the excitation source of ZSCCs, i.e., the difference in common mode voltages (CMVs) between paralleled inverters, the ZCMV-PWM method is presented to reduce CMVs, and a simple electric circuit is adopted to control ZSCCs and neutral point potential. Finally, simulation and experiment are conducted to illustrate effectiveness of the proposed strategy. Results show that ZSCCs between paralleled inverters can be eliminated effectively under steady and dynamic states. Moreover, the proposed strategy exhibits the advantage of not requiring carrier synchronization. It can be utilized in inverters with different types of filter.

Statistical and systematic challenges in collaboratively training machine learning models across distributed networks of mobile devices have been the bottlenecks in the real-world application of federated learning. In this work, we show that meta-learning is a natural choice to handle these issues, and propose a federated meta-learning framework FedMeta, where a parameterized algorithm (or meta-learner) is shared, instead of a global model in previous approaches. We conduct an extensive empirical evaluation on LEAF datasets and a real-world production dataset, and demonstrate that FedMeta achieves a reduction in required communication cost by 2.82-4.33 times with faster convergence, and an increase in accuracy by 3.23%-14.84% as compared to Federated Averaging (FedAvg) which is a leading optimization algorithm in federated learning. Moreover, FedMeta preserves user privacy since only the parameterized algorithm is transmitted between mobile devices and central servers, and no raw data is collected onto the servers.