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。

Complement Objective Training with Pytorch Lightning

4 点作者 talolard将近 4 年前

1 comment

talolard将近 4 年前
Hi HN, I wrote this and wanted to share a few more words. This post discusses a trick for training neural networks. Usually when we train a NN, we just show it what the correct answer is, but we don&#x27;t say anything explicit about the wrong answers. This trick, Complement Objective Training, is a way to give the model &quot;feedback about its mistakes&quot;. In practice, it makes the model better and train faster.<p>The important thing is that it&#x27;s pretty easy to implement. Many cool research ideas are a months work, but this takes 15 minutes with pytorch lighting so it&#x27;s in the realm of low hanging fruit.
评论 #27674104 未加载