arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1409.4469nlin.PScond-mat.dis-nncs.CV
收藏

耦合振子阵列卷积网络图像处理

Convolutional Networks for Image Processing by Coupled Oscillator Arrays

Intel Corp.(英特尔公司)

Dmitri E. Nikonov, Ian A. Young, George I. Bourianoff

摘要:

耦合振荡器阵列示出近似卷积与Gabor滤波器的图像处理任务。像素化的图像片段和滤波器函数被转换为电压,差分,并输入到弱耦合压控振荡器(VCO)的相应阵列中。这被称为频移键控(FSK)。在阵列同步时,公共节点幅度提供图像片段与滤波器函数之间的匹配程度的度量。用于同步的最佳振荡器参数被确定并且有利于Q因子的中等值。

英文摘要:

A coupled oscillator array is shown to approximate convolutions with Gabor filters for image processing tasks. Pixelated image fragments and filter functions are converted to voltages, differenced, and input into a corresponding array of weakly coupled Voltage Controlled Oscillators (VCOs). This is referred to as Frequency Shift Keying (FSK). Upon synchronization of the array, the common node amplitude provides a metric for the degree of match between the image fragment and the filter function. The optimal oscillator parameters for synchronization are determined and favor a moderate value of the Q-factor.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑