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。

Ask HN: Has anyone tried to search for new, basic machine learning operations?

1 点作者 reedwolf大约 5 年前
E.g. primitive operations like convolution and pooling.<p>From Neural Architecture Search: A Survey[0], first published in 2018:<p>&quot;Moreover, common search spaces are also based on predefined building blocks, such as different kinds of convolutions and pooling, but do not allow identifying novel building blocks on this level; going beyond this limitation might substantially increase the power of NAS.&quot;<p>I wonder now if somebody tried that since this was written or if anybody has some thoughts about the feasibility of this idea.<p>We&#x27;ve been using these methods for years. I doubt the first few breakthroughs are the most optimal possible.<p>[0]https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1808.05377

暂无评论

暂无评论