replying to N. Dennler et al. Nature Machine Intelligence https://doi.org/10.1038/s42256-024-00952-1 (2024)

In their Comment, Dennler et al.¹ submit that they have discovered limitations affecting some of the conclusions drawn in our 2020 paper, ‘Rapid online learning and robust recall in a neuromorphic olfactory circuit’². Specifically, they assert (1) that the public dataset we used suffers from sensor drift and a non-randomized measurement protocol, (2) that our neuromorphic external plexiform layer (EPL) network is limited in its ability to generalize over repeated presentations of an odourant, and (3) that our EPL network results can be performance matched by using a more computationally efficient distance measure. Although they are correct in their description of the limitations of that public dataset³, they do not acknowledge in their first two assertions how our utilization of those data sidestepped these limitations. Their third claim arises from flaws in the method used to generate their distance measure. We respond below to each of these three claims in turn.

replying to N. Dennler et al. Nature Machine Intelligence https://doi.org/10.1038/s42256-024-00952-1 (2024)

在他们的评论中，Dennler 等人^{1 提出，}他们发现了影响我们 2020 年论文“神经形态嗅觉回路中的快速在线学习和稳健回忆”² 中得出的一些结论的局限性。具体来说，他们断言 （1） 我们使用的公共数据集受到传感器漂移和非随机测量协议的影响，（2） 我们的神经形态外部丛状层 （EPL） 网络在对气味的重复呈现进行泛化的能力方面受到限制，以及 （3） 我们的 EPL 网络结果可以通过使用计算效率更高的距离测量来匹配性能。尽管他们对公共数据集³ 的局限性的描述是正确的，但他们在前两个断言中没有承认我们对这些数据的利用是如何避开这些局限性的。他们的第三个主张源于用于生成距离测量的方法中的缺陷。我们在下面依次回应这三种说法。