Direction of arrival (DOA) refers to finding direction information of propagating waves from the received antennas equipped with several sensors. Recently, we have witnessed an enrichment of source data prompting us to design more robust DOA estimator, where artificial neural network (ANN)- based DOA estimators have shown their superior performance as compared to the traditional subspace-based DOA estimation methods. However, these data-driven DOA estimation methods tend to rely on parameters that are computationally intensive for efficient processing/running with the limitation of hardware resources. Thus, we propose an event-driven spiking neural network (SNN) model, namely, Joint-Scnn, for DOA in the presence of various imperfections, which consists of ANN-based and SNN-based modules with weights sharing. The former not only contributes to assist sparse SNN-based module to learn latent information, but also enhances its robustness via selflearning. The superior estimation performance and lower power consumption have been verified via experimental results. The success of Joint-Scnn is partially attributed to the teacherstudent tandem learning scheme.

The W-band staggered double vane Slow Wave Structure (SWS)Travelling Wave Tube (TWT) adopting the negative phase-velocity tapering technique is proposed and investigated in this paper, benefiting the improvement of the output power. The input/output coupler, which uses resonators to feed electromagnetic waves into SWS, for this kind of SWS are put forward. It is not only simple to manufacture, but also greatly reduces the longitudinal size of the TWT. In this paper, the high frequency characteristics, transmission characteristics and beam-wave interaction are analyzed by simulation software. The particle-in-cell results show that its output power and gain at 91 GHz can reach 1800 W and 10.5 dB, respectively. Its 3-dB bandwidth is from 87 GHz to 96 GHz. Based on these, the experiment of the fabricated high frequency system with filleted staggered double vane slow wave structure is carried out.

The recent advances in artificial neural networks (ANNs) have created immense opportunities to achieve excellent results on the Internet of Things (IoT), which serve the uses of various real-time smart applications, such as in computer vision and speech recognition. However, the efficiency of ANNs comes at the expense of a huge number of computational resources. This tends to necessitate larger and wider ANNs unapplicable for embedded systems with limited hardware resources, e.g., mobile and wearable devices. To that end, biologically realistic spiking neural networks (SNNs) are first employed to build an always-on intelligent and connected integrated IoT-enabled system with ultralow power consumption, where we encode the temporal dynamic stimuli into effective, efficient, and reconstructable spike patterns to facilitate the subsequent processing. Herein, neural encoding plays a key role in faithfully describing the temporally rich patterns for downstream cognitive tasks. Therefore, a novel nonlinear piecewise latency coding approach for a fully event-driven SNN system is developed. Moreover, a surrogate postsynaptic potential kernel function is utilized to address the nondifferential nature of the spike generation scheme when using the error backpropagation learning method. The effectiveness of the proposal tandem with SNNs has been corroborated by indicative empirical results on different data sets serving cognitive tasks.

Spiking neural networks (SNNs) use spatiotemporal spike patterns to represent and transmit information, which are not only biologically realistic but also suitable for ultralow-power event-driven neuromorphic implementation. Just like other deep learning techniques, deep SNNs (DeepSNNs) benefit from the deep architecture. However, the training of DeepSNNs is not straightforward because the well-studied error backpropagation (BP) algorithm is not directly applicable. In this article, we first establish an understanding as to why error BP does not work well in DeepSNNs. We then propose a simple yet efficient rectified linear postsynaptic potential function (ReL-PSP) for spiking neurons and a spike-timing-dependent BP (STDBP) learning algorithm for DeepSNNs where the timing of individual spikes is used to convey information (temporal coding), and learning (BP) is performed based on spike timing in an event-driven manner. We show that DeepSNNs trained with the proposed single spike time-based learning algorithm can achieve the state-of-the-art classification accuracy. Furthermore, by utilizing the trained model parameters obtained from the proposed STDBP learning algorithm, we demonstrate ultralow-power inference operations on a recently proposed neuromorphic inference accelerator. The experimental results also show that the neuromorphic hardware consumes 0.751 mW of the total power consumption and achieves a low latency of 47.71 ms to classify an image from the Modified National Institute of Standards and Technology (MNIST) dataset. Overall, this work investigates the contribution of spike timing dynamics for information encoding, synaptic plasticity, and decision-making, providing a new perspective to the design of future DeepSNNs and neuromorphic hardware.

Feature extractionplays an important role before pattern recognition takes place. The existing artificial neural networks (ANNs), however, ignoreto learn and represent temporal information, instead of only utilizing spatial information for recognition. Moreover, the substantial computational and energy costs resulted from the conventional ANN-based classifiers, limit their uses in mobile and embedded applications. In this work, we develop a sparse temporal encoding method which exploits both spatial and temporal information. On the basis of spike-timing-dependent plasticity and multi-scale structure, the resulting temporal feature representation integrates with a temporal spiking neural network (SNN) classifier to achieve high efficiency of parallel computing for feature extraction. Experimental evaluation on four benchmark datasets from image classification and speech recognition tasks show the proposed SNN model yielding state-of-the-art accuracy.