Neuromorphic computing using spike‐based learning has broad prospects in reducing computing power. Memristive neurons composed with two locally active memristors have been used to mimic the dynamical behaviors of biological neurons. Herein, the dynamic operating conditions of NbO2‐based memristive neurons and their transformation boundaries between the spiking and the bursting are comprehensively investigated. Furthermore, the underlying mechanism of bursting is analyzed, and the controllability of the number of spikes during each burst period is demonstrated. Finally, pattern classification and information transmitting in a perceptron neural network by using the number of spikes per bursting period to encode information is proposed. The results show a promising approach for the practical implementation of neuristor in spiking neural networks.

Nature positively embodies a rich yet complex array of nonlinear phenomena. To date, it has remained unclear how to exploit these phenomena to solve a wide range of problems. The Van der Pol oscillator is one of the nonlinear dynamical systems that hold tremendous promise for a broad range of important applications from a circuit performance booster to hard problem solving to mapping the biological nonlinear dynamics. Here, we theoretically build a Van der Pol oscillator circuit using a NbO2 volatile memristor to perform a systematic analysis of the complex nonlinear dynamic behavior. Three types of oscillation phenomena including period doubling, quasi-period, and chaos are obtained by varying the parallel capacitance and futher distinguished by mathematical analysis, such as fast Fourier transform, Poincaré plots, and plane trajectories of voltage on the memristor. The frequency locking phenomenon of the system is presented to enable a programmable frequency demultiplication. Moreover, the other critical circuit parameters such as DC voltage amplitude, load resistance, and AC driving frequency are also modulated to understand the nonlinear dynamic behavior of the system. All these analyses provide a viable platform to understand and implement nonlinear systems for a broad range of multifunctional oscillatory devices.

Obtaining Road information from high-resolution remote sensing images (HRSI) is gaining attention in intelligent transportation systems. Existing road extraction methods tend to improve road connectivity with graph convolution or global attention, however, ignore the damage of introduced excessive effective receptive field (ERF) to multi-scale road details. In this study, we propose an Auxiliary-Decoding Road Extraction Network named AD-RoadNet which decouples multi-scale road representation and connectivity improvement based on two modules; the Hybrid Receptive Field Module (HRFM) and the Topological Feature Representation Module (TFRM). The HRFM is introduced in the encoder to emphasize target road features through adaptively matching the receptive field (RF) size for various scale roads, thus beneficial for multi-scale road representation. The TFRM is introduced in an auxiliary decoder to represent topological features with the position information encoded in the shared encoder and then helps the main decoder reason occluded roads, thus improving connectivity. Between the encoder and main decoder. The proposed model has a similar parameter scale as HRNetV2 and outperforms the state-of-the-art ResUnet, D-LinkNet, and HRNetV2 by 3.34%, 2.03%, and 1.53% in the mean Intersection of Union (mIoU) on DeepGlobe Road Dataset. Ablation analysis, inference size matter, and the robustness for unseen occlusion scenarios, low-quality labels, and various quality inference images are further presented to evaluate the proposed AD-RoadNet.