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。

Probabilistic programming does in 50 lines of code what used to take thousands

164 点作者 ub大约 10 年前

10 条评论

jb55大约 10 年前
If anyone wants to jump into this, Josh Tenenbaum and Noah Goodman put together this amazing interactive book for learning probabilistic programming with Church: <a href="https:&#x2F;&#x2F;probmods.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;probmods.org&#x2F;</a>
评论 #9371905 未加载
stevenspasbo大约 10 年前
Is that 50 lines of code, or 50 lines of using a library that&#x27;s thousands of lines of code?
评论 #9369682 未加载
评论 #9369594 未加载
评论 #9368957 未加载
评论 #9370576 未加载
评论 #9371396 未加载
评论 #9370429 未加载
评论 #9369831 未加载
评论 #9372777 未加载
评论 #9370324 未加载
cheatsheet大约 10 年前
&gt; “It goes beyond image classification — the most popular task in computer vision — and tries to answer one of the most fundamental questions in computer vision: What is the right representation of visual scenes?<p>Can someone knowledgeable in graphics research explain the context that this question comes from?<p>If I am reading the question correctly, I infer that the question suggests that there exists a right way to reproduce the visual experience of reality. To me, this sounds like a question that is equally valid to have no answer (or many answers) in aesthetics, art, and philosophy, etc.
评论 #9369519 未加载
评论 #9370682 未加载
评论 #9369253 未加载
评论 #9369338 未加载
murbard2大约 10 年前
Yes, you can specify extremely powerful statistical models in only a few lines of code using probabilistic programming.<p>However, at this point, unless you design your program in a very specific way and use a lot of tricks, your sampler is very unlikely to converge, and you won&#x27;t get any meaningful result without a gargantuan amount of computing power.
dang大约 10 年前
Also <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=9363496" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=9363496</a> from yesterday.
ub大约 10 年前
No experience but looks like they are organizing a summer school on probabilistic programming languages. <a href="http:&#x2F;&#x2F;ppaml.galois.com&#x2F;wiki&#x2F;wiki&#x2F;SummerSchools&#x2F;2015&#x2F;Announcement" rel="nofollow">http:&#x2F;&#x2F;ppaml.galois.com&#x2F;wiki&#x2F;wiki&#x2F;SummerSchools&#x2F;2015&#x2F;Announc...</a>
pliny大约 10 年前
relevant paper: <a href="http:&#x2F;&#x2F;mrkulk.github.io&#x2F;www_cvpr15&#x2F;1999.pdf" rel="nofollow">http:&#x2F;&#x2F;mrkulk.github.io&#x2F;www_cvpr15&#x2F;1999.pdf</a>
评论 #9371859 未加载
newpattern大约 10 年前
Anybody here on HN have experience with probabilistic-programming ? This looks quite disruptive if it works.
评论 #9370502 未加载
评论 #9368980 未加载
评论 #9369490 未加载
评论 #9370038 未加载
评论 #9368837 未加载
eli_gottlieb大约 10 年前
Ah, so they wrote a DSL just for doing Bayesian inverse-vision models, and apparently they&#x27;ve now got it to accuracy rates competitive with most other major vision methods?<p>Good job!
contingencies大约 10 年前
Probabilistic prediction: this is primarily going to be used for robots that monitor, kill or assist with killing people.
评论 #9372094 未加载