TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

A computational model of the Moth Olfactory Network learns to read MNIST [pdf]

71 点作者 higgsfield超过 7 年前

5 条评论

carbocation超过 7 年前
For some reason, Figure 2 doesn't continue out beyond the few-training-samples regime. Therefore, I think we're left to assume that MothNet underperforms the other techniques in the many-samples regime. Is there something I'm missing?
评论 #16367214 未加载
lootsauce超过 7 年前
Yet to read this paper but wondering if the authors a familiar with the work of Dasgupta et al. on fly olfactory model for locality sensitive hashing?<p><a href="https:&#x2F;&#x2F;www.biorxiv.org&#x2F;content&#x2F;biorxiv&#x2F;early&#x2F;2017&#x2F;08&#x2F;25&#x2F;180471.full.pdf?%3Fcollection=" rel="nofollow">https:&#x2F;&#x2F;www.biorxiv.org&#x2F;content&#x2F;biorxiv&#x2F;early&#x2F;2017&#x2F;08&#x2F;25&#x2F;180...</a><p>I have been contemplating the relationship between random projections and compressive sensing since reading it and curious to read this paper for any insights on compressive sensing.
memebox3v超过 7 年前
This is absolutely brilliant. I have been looking for a way into an understanding of learning within biological neural nets. I dont suppose there is source code around?
robinduckett超过 7 年前
So are we learning that brains and neurons are general purpose computation goo that can be applied to many different areas of signal processing yet?
评论 #16370193 未加载
评论 #16370952 未加载
fovc超过 7 年前
Needs a [pdf] flag
评论 #16368019 未加载
评论 #16369832 未加载