The transient stability assessment (TSA) is of paramount importance for the long-term safe and stable operation of power systems. However, traditional assessment methods are unable to adapt to the increasingly demandi...
详细信息
When an aircraft suffers a lightning strike, the cables are coupled with overvoltages by the pulsed electromagnetic field generated from the lightning current, probably resulting in damage towards the electrical and e...
详细信息
Deep reinforcement learning(DRL) achieves success through the representational capabilities of deep neural networks(DNNs). Compared to DNNs, spiking neural networks(SNNs),known for their binary spike information proce...
详细信息
Deep reinforcement learning(DRL) achieves success through the representational capabilities of deep neural networks(DNNs). Compared to DNNs, spiking neural networks(SNNs),known for their binary spike information processing, exhibit more biological characteristics. However, the challenge of using SNNs to simulate more biologically characteristic neuronal dynamics to optimize decision-making tasks remains, directly related to the information integration and transmission in *** by the advanced computational power of dendrites in biological neurons, we propose a multi-dendrite spiking neuron(MDSN) model based on Multi-compartment spiking neurons(MCN), expanding dendrite types from two to multiple and deriving the analytical solution of somatic membrane *** apply the MDSN to deep distributional reinforcement learning to enhance its performance in executing complex decisionmaking tasks. The proposed model can effectively and adaptively integrate and transmit meaningful information from different sources. Our model uses a bioinspired event-enhanced dendrite structure to emphasize features. Meanwhile, by utilizing dynamic membrane potential thresholds, it adaptively maintains the homeostasis of MDSN. Extensive experiments on Atari games show that the proposed model outperforms some state-of-the-art spiking distributional RL models by a significant margin.
作者：
Xiao, JvlongLiu, Kexin
School of Automation Science and Electrical Engineering Beijing100191 China
This paper proposes a distributed quantified shape-formation algorithm that incorporates communication quantification in consensus negotiation during motion control. This algorithm encourages all agents to reach a con...
详细信息
Determining the maximum force feedback control cycle time for an assembly task at a given force/torque threshold is an important basis for designing and evaluating the corresponding force-compliant assembly method. Fo...
详细信息
Considering the few reports on the near-field acoustic pressure signals initiated from lightning return strokes focusing on the acoustic characteristics and the correlation with discharge parameters, in the summer of ...
详细信息
Rapid diagnosis and real-time monitoring are of great important in the fight against ***,most available diagnostic technologies are time-consuming and labor-intensive and are commonly ***,we describe CytoExam,an autom...
详细信息
Rapid diagnosis and real-time monitoring are of great important in the fight against ***,most available diagnostic technologies are time-consuming and labor-intensive and are commonly ***,we describe CytoExam,an automatic liquid biopsy instrument designed based on inertial microfluidics and impedance cytometry,which uses a deep learning algorithm for the analysis of circulating tumor cells(CTCs).In silico and in vitro experiments demonstrated that CytoExam could achieve label-free detection of CTCs in the peripheral blood of cancer patients within 15 *** clinical applicability of CytoExam was also verified using peripheral blood samples from 10 healthy donors and>50 patients with breast,colorectal,or lung *** differences in the number of collected cells and predicted CTCs were observed between the 2 groups,with variations in the dielectric properties of the collected cells from cancer patients also being *** ultra-fast and minimally invasive features of CytoExam may pave the way for new paths for cancer diagnosis and scientific research.
Given the frequent occurrence of rolling bearing faults, to effectively enhance the accuracy of rolling bearing fault diagnosis, this paper constructs a bearing fault diagnosis classifier using a Light Gradient Boosti...
详细信息
As a new technology, magnetic target detection technology has many advantages, such as low cost, fast and reliable, low environmental impact and so on. At present, there are many kinds of magnetic target detection tec...
详细信息
Convolutional Neural Networks (CNNs) are a powerful tool in computer vision, excelling at tasks like image classification and object detection. The need for low latency and strict power consumption in real-world appli...
详细信息
暂无评论