arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12557cs.NEcond-mat.dis-nn
收藏

使用自旋波延迟线有源环储备池计算的语音数字分类

Spoken digit classification using a spin-wave delay-line active-ring reservoir computing

Stuart Watt, Mikhail Kostylev

摘要:

作为普遍适用性的测试,我们使用最近提出的自旋波延迟线有源环库计算机来执行口语数字识别任务。在此基础上,实现了高达93%的分类准确率。测试的设备原型采用改进的自旋波换能器(天线)。因此,除此之外,我们还让计算机完成短时记忆(STM)任务和奇偶检验(PC)任务,因为衰减记忆和非线性对储备池计算性能至关重要。所得STM和PC容量分别达到最大值4.77和1.47。

英文摘要:

As a test of general applicability, we use the recently proposed spin-wave delay line active-ring reservoir computer to perform the spoken digit recognition task. On this, classification accuracies of up to 93% are achieved. The tested device prototype employs improved spin wave transducers (antennas). Therefore, in addition, we also let the computer complete the short-term memory (STM) task and the parity check (PC) tasks, because the fading memory and nonlinearity are essential to reservoir computing performance. The resulting STM and PC capacities reach maximum values of 4.77 and 1.47 respectively.

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。

↑