Zobrazeno 1 - 10
of 522
pro vyhledávání: '"XIAO MingQing"'
Brain-inspired neuromorphic computing with spiking neural networks (SNNs) is a promising energy-efficient computational approach. However, successfully training SNNs in a more biologically plausible and neuromorphic-hardware-friendly way is still cha
Externí odkaz:
http://arxiv.org/abs/2407.12516
Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation, distinguished by their computational capability and energy efficiency due to precise spiking times and sparse spikes with event-driven computation.
Externí odkaz:
http://arxiv.org/abs/2405.16851
Publikováno v:
He jishu, Vol 45, Iss 7, Pp 070603-070603 (2022)
BackgroundTritium leakage is a typical nuclear accident scene, which is harmful to human and environment. Therefore, numerical simulation of tritium leakage is of significance to nuclear accident emergency decision making.PurposeThis study aims at th
Externí odkaz:
https://doaj.org/article/d932f70f83d2433cb989fde1a5f0b34d
Publikováno v:
Advances in Civil Engineering, Vol 2021 (2021)
A series of local prototype tests are conducted on the Sutong GIL (Gas-Insulated Line) and Shiziyang Tunnel. These tests investigate the redistribution law of segment deformation and the bending moment during construction. The results reveal that the
Externí odkaz:
https://doaj.org/article/0d1c3fde048741efa0771674eca4e660
Publikováno v:
Jixie qiangdu, Vol 41, Pp 1151-1157 (2019)
An accelerated life test is designed and a kind of analysis method for solenoid valve failure based on multi-physics finite element model is put forward due to the uncertainty of failure mechanism and the lack of effective means to analyze faults. Fi
Externí odkaz:
https://doaj.org/article/dacc9574c99846ef9d018fc3e417a214
Neuromorphic computing with spiking neural networks is promising for energy-efficient artificial intelligence (AI) applications. However, different from humans who continually learn different tasks in a lifetime, neural network models suffer from cat
Externí odkaz:
http://arxiv.org/abs/2402.11984
Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high performanc
Externí odkaz:
http://arxiv.org/abs/2302.14311
Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. However, most supervised SNN training methods, such as conversion from artificial neural netwo
Externí odkaz:
http://arxiv.org/abs/2302.00232
Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. Particularly, backpropagation through time (BPTT) with su
Externí odkaz:
http://arxiv.org/abs/2210.04195
Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution images to recov
Externí odkaz:
http://arxiv.org/abs/2210.04188