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。

Learn ML through live team competitions, not lectures

115 点作者 henry_pulver将近 3 年前

8 条评论

riedel将近 3 年前
We do this as part of our university practical course as well (2 week challenges in teams of 4, sometimes participating also in external competitions). While I agree that this good for learning, I would, however, say it is completary to lectures. It makes no sense if people just learn to overfit some hyperparams to beat a score. So rating should at least be done wisely. Otherwise I think people need lectures to understand the real limits of tech and actually find novel uses.<p>With many good lecture contents online I think it also would be good to also switch to more live competitions at university to do inverted classroom style learning. I think it is the mix that matters (along with the quality)
Barrin92将近 3 年前
Every time I read a slogan like &quot;learn X in Y weeks&quot; or &quot;learn through games instead of lectures&quot;, I have to think of a Peter Norvig piece: <i>Teach Yourself Programming in Ten Years</i>.<p>Honestly instead of taking paid courses that promise to teach incredibly difficult subjects in weeks, just take one of the longer courses like Andrew Ng&#x27;s that start with the fundamentals and are free. Bootcamp style education is awful.<p><a href="https:&#x2F;&#x2F;norvig.com&#x2F;21-days.html" rel="nofollow">https:&#x2F;&#x2F;norvig.com&#x2F;21-days.html</a>
评论 #31710747 未加载
评论 #31715416 未加载
cosentiyes将近 3 年前
&gt; Learn reinforcement learning in 4 weeks<p>There are so many high quality, free resources online for learning RL [1,2,...]. Four weeks of primarily self-guided M-F study isn&#x27;t nearly enough time to obtain anything more than a cursory understanding of the topic. Kaggle, various gym environment baselines, and workshop competitions exist for those who want to compete.<p>[1] <a href="https:&#x2F;&#x2F;www.deepmind.com&#x2F;learning-resources&#x2F;introduction-to-reinforcement-learning-with-david-silver" rel="nofollow">https:&#x2F;&#x2F;www.deepmind.com&#x2F;learning-resources&#x2F;introduction-to-...</a> [2] <a href="http:&#x2F;&#x2F;incompleteideas.net&#x2F;book&#x2F;the-book-2nd.html" rel="nofollow">http:&#x2F;&#x2F;incompleteideas.net&#x2F;book&#x2F;the-book-2nd.html</a>
hetzenmat将近 3 年前
Everytime I read something like &quot;learn ML&quot; I think about learning some descendant of the ML programming language like OCaml, F# or Standard ML instead of machine learning.
评论 #31705970 未加载
评论 #31706169 未加载
评论 #31705838 未加载
sva_将近 3 年前
The price seems a bit steep to participate in a competition (60 USD for a month)
评论 #31705878 未加载
crimsoneer将近 3 年前
At the risk of sounding like an utter moron, is anybody else struggling to pay (option to add name and address to the payment card are greyed out?)
tpoacher将近 3 年前
I learned surgery the same way. Swathes of punctured spleens aside, it was a lot of fun!<p>&#x2F;s
cultofmetatron将近 3 年前
how does this compare to kaggle?
评论 #31705842 未加载