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。

On the Origin of Circuits (2007)

52 点作者 chwolfe将近 10 年前

5 条评论

crimsonalucard将近 10 年前
Does anyone know of any projects where they use a different set of primitives? In this article it&#x27;s logic gates and real world electromagnetic phenomena, in neural nets it&#x27;s neurons....<p>Have there ever been experiments that tried using 3D primitives or even language primitives from programming languages? There&#x27;s almost an unlimited amount of possible input primitives, yet the industry seems to only focus on neural nets.
评论 #9889779 未加载
natosaichek将近 10 年前
This project strikes me as similar. Evolve a computational network and train it in the real world:<p><a href="http:&#x2F;&#x2F;www.ouroboros.org&#x2F;evo_gaits.html" rel="nofollow">http:&#x2F;&#x2F;www.ouroboros.org&#x2F;evo_gaits.html</a>
nickpsecurity将近 10 年前
I dabble in this stuff on occasion and enjoy reading about it. My first favorite was Danny Hillis&#x27; story [1] about designing sorting algorithms using genetic algorithms on a massively parallel machine. He also showed the power of co-evolution: both solutions and tests evolve. Later, I saw the HUMIE awards [2] show off what people have accomplished. Then, there was the nice article [3] on John Koza&#x27;s Invention Machine. Plenty to get a person interested in the stuff.<p>Yet, most of it happens in academia and paid industry with a lot of good information not easily accessible to non-experts. There&#x27;s not as much momentum in developing easy to use tools and frameworks for most use cases like we see with, say, web applications. This limits the field to people willing to put in significant time in understanding the subject, the methods, their strengths&#x2F;limitations, and the various implementations out there.<p>Nonetheless, I at least enjoy reading the abstracts and know I could contract a specialist for a certain applications.<p>[1] <a href="http:&#x2F;&#x2F;kk.org&#x2F;mt-files&#x2F;outofcontrol&#x2F;ch15-d.html" rel="nofollow">http:&#x2F;&#x2F;kk.org&#x2F;mt-files&#x2F;outofcontrol&#x2F;ch15-d.html</a><p>[2] <a href="http:&#x2F;&#x2F;www.genetic-programming.org&#x2F;combined.html" rel="nofollow">http:&#x2F;&#x2F;www.genetic-programming.org&#x2F;combined.html</a><p>[3] <a href="http:&#x2F;&#x2F;www.popsci.com&#x2F;scitech&#x2F;article&#x2F;2006-04&#x2F;john-koza-has-built-invention-machine" rel="nofollow">http:&#x2F;&#x2F;www.popsci.com&#x2F;scitech&#x2F;article&#x2F;2006-04&#x2F;john-koza-has-...</a>
bsder将近 10 年前
The problem with &quot;evolutionary&quot; circuits is that 99.99% of them don&#x27;t work very well (dead organisms).<p>And that .01% often optimizes some weird corner case that kinda, sorta works but isn&#x27;t really a &quot;solution&quot; (sickle cell anemia).<p>And in the .000001% case generates something genuinely useful (vision).<p>Gee, sort of like actual evolution, no?
评论 #9890082 未加载
hammock将近 10 年前
I really hope some commentary develops from HN on this
评论 #9888310 未加载
评论 #9888481 未加载