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。

Private Multi-Party Machine Learning

22 点作者 alex_hirner超过 8 年前

2 条评论

webmaven超过 8 年前
Slides from the scheduled presentations[0], as well as most of the accepted papers[1], are available.<p>This is some seriously mind-bending stuff. Google is represented by a couple of papers, but I was really hoping that the privacy-preserving techniques they used in training the network for Inbox Smart Replies would be explained. No such luck.<p>[0] <a href="https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#schedule" rel="nofollow">https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#schedule</a><p>[1] <a href="https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#papers" rel="nofollow">https:&#x2F;&#x2F;pmpml.github.io&#x2F;PMPML16&#x2F;#papers</a>
jhoechtl超过 8 年前
I wonder why nobody of these guys has been there <a href="http:&#x2F;&#x2F;www.enigma.co" rel="nofollow">http:&#x2F;&#x2F;www.enigma.co</a>