共 3 篇文章 |
|
1.Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate Coding and Co Mapping from Frame-Driven to Frame-Free Event-Driven Vision Systems by Low-Rate Rate Coding and Coincidence Processing—Application to Feedforward ConvNets.事件驱动传感器是一种特殊类型的事件,即所谓的动态视觉传感器(DVS),其中每个像素都计算光线或“时间对比度”的相对变化。事件驱动的ConvNet使用专用的事件驱动模拟器进行... 阅111 转0 评0 公众公开 19-12-16 16:41 |
Spiking Deep Residual Network.To address the conversion problem, we propose a shortcut normalisation mechanism to appropriately scale continuous-valued activations to match firing rates in SNN, and a layer-wise error compensation approach to reduce the error caused by discretisation. 为了解决转化过程中的问题,文章提出... 阅26 转0 评0 公众公开 19-12-16 15:48 |