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。

Combinatorial optimization with reinforcement learning

28 点作者 higgsfield超过 7 年前

1 comment

2bitencryption超过 7 年前
I&#x27;ve always wondered how deep learning handles problems with well-understood time complexities.<p>How well does the idea of &quot;time complexity&quot; apply to a NN? Since we aren&#x27;t performing a series of operations with a NN, we are just passing values through a mesh of neurons, right?<p>Would we ever know if a NN &quot;found&quot; a way to solve a certain problem in a more efficient time complexity than what we currently understood? Can the &quot;time complexity&quot; concept evne apply to a NN?
评论 #16007554 未加载