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。

Growing Neural Cellular Automata (2020)

49 点作者 grlass超过 3 年前

4 条评论

OttPeterR超过 3 年前
If this is your first time hearing about distill, they have so many more articles that are of equally astounding quality. I’ve been reading them for a while now and love what they do!
评论 #28536245 未加载
mrtnmcc超过 3 年前
Why use differentiable models here, it seems like a big limitation to CA just to allow back-prop. Can't these be trained with genetic algorithms or evolutionary methods like SPSA?
K5EiS超过 3 年前
Very cool! Managed to put the butterfly in an loop.<p><a href="https:&#x2F;&#x2F;i.imgur.com&#x2F;cStndTQ.png" rel="nofollow">https:&#x2F;&#x2F;i.imgur.com&#x2F;cStndTQ.png</a>
lerax超过 3 年前
That is a pretty interesting work. Maybe a model derivation of this can be image (historic) restoration or new noise filters?