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。

Bayesian Deep Learning

7 点作者 twiecki将近 9 年前

1 comment

lotsoflumens将近 9 年前
Very nice article!<p>But ... You generated your original data from: &quot;sklearn.datasets.make_moons&quot;. Then you say that you tested your classifier on a hold-out set with &quot;sample_ppc()&quot;.<p>I don&#x27;t think that&#x27;s a true hold-out set. A true hold-out set would be obtained by running &quot;make_moons()&quot; again to generate new data.<p>Have you tried that? It would be interesting I think.<p>I&#x27;ll run the test myself too ...<p>Again, thanks for a very nice and informative article.
评论 #11817216 未加载