Quantification of a Spike-Based Winner-Take-All VLSI Network
Quantification of a Spike-Based Winner-Take-All VLSI Network
复制标题
基于尖峰的赢家通吃 VLSI 网络的量化
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
Shih
中科院分区：
文献类型：
--
作者：
M. Oster;Yingxue Wang;R. Douglas;Shih
我们描述了一种量化基于尖峰的赢家通吃 (WTA) VLSI 芯片性能的形式。 WTA 函数根据决策或选择任务中的输入幅度非线性放大像素/神经元的输出响应。在本文中，我们展示了这种 WTA 计算的理论描述，其中考虑了输入统计数据、神经元响应方差和输出率。该分析在采用 4 金属、2 聚 0.35-mum CMOS 工艺制造的尖峰 VLSI 神经元网络上进行了测试。该芯片的 WTA 性能测量结果与理论预测相符。这种形式可以应用于任何基于尖峰的神经元的实现。
We describe a formalism for quantifying the performance of spike-based winner-take-all (WTA) VLSI chips. The WTA function nonlinearly amplifies the output responses of pixels/neurons dependent on the input magnitudes in a decision or selection task. In this paper, we show a theoretical description of this WTA computation which takes into consideration the input statistics, neuron response variance, and output rates. This analysis is tested on a spiking VLSI neuronal network fabricated in a 4-metal, 2-poly 0.35-mum CMOS process. The measured results of the WTA performance from this chip correspond to the theoretical prediction. This formalism can be applied to any implementation of spike-based neurons.