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。

Building a Language and Compiler for Machine Learning

161 点作者 one-more-minute超过 6 年前

5 条评论

ChrisRackauckas超过 6 年前
As someone who works in merging differential equations and machine learning, I have found this kind of work essential for what I do. Pervasive AD that allows merging neural networks and diffeq solvers is allowing us to explore all of kinds of new models and new problems. Sure it doesn't impact vanilla machine learning all that much (though Zygote.jl does allow for a lot of optimizations that wouldn't be possible with tracing-based AD), but it definitely opens up a new wave of AI possibilities.
评论 #18602990 未加载
评论 #18603488 未加载
评论 #18602674 未加载
manojlds超过 6 年前
<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=18593453" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=18593453</a>
yahyaheee超过 6 年前
I’m finding the ML work being done in Julia very refreshing. It feels like they are building things right from the ground up and the community is great to work with.
pbalau超过 6 年前
&gt; [...] bake for fifteen minutes and out pops a fully-featured ML stack<p>where is logging, where is model storage and versioning, where is input data processing and normalizing, where is results processing?
评论 #18602650 未加载
评论 #18602688 未加载
xvilka超过 6 年前
Hopefully one day Julia won&#x27;t need patched LLVM. Will improve packaging in various distributions too.