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。

How to learn Deep Learning in 6 months

89 点作者 antonp超过 7 年前

6 条评论

YeGoblynQueenne超过 7 年前
Here&#x27;s Peter Norvig arguing that you shouldn&#x27;t:<p><i>Teach Yourself Programming in Ten Years</i><p><a href="https:&#x2F;&#x2F;www.norvig.com&#x2F;21-days.html" rel="nofollow">https:&#x2F;&#x2F;www.norvig.com&#x2F;21-days.html</a><p>The article is about programming, specifically about books etc advising you on how to learn programming in ten days etc, but it totally applies to Deep Learnign also.<p>Deep Learning is an enormous discipline. In the current point in the hype cycle, there are literally thousands of papers published every month. Personally, I doubt anyone, evern the luminaries of the field are keeping up with it. 6 months is about enough to dip your toes into the preliminaries, and that&#x27;s if you&#x27;re willing to skip the relative background [1].<p>Of course, that&#x27;s all true if you want to <i>learn</i>. If you just want to train yourself in the use of a few tools, then 6 months is plenty. But don&#x27;t expect to be able to solve any new problems that way- someone else will always have to do all the hard work for you.<p>________<p>[1] A bit of background will help with questions such as: Why was Deep Learning necessary in the first place? (hint: search for &quot;constant error carousel&quot;); did Deep Learning just spring fully-formed from the brow of Hinton&#x2F; Schmidhuber? (hint: read wikipedia on &quot;machine learning&quot; and &quot;Artificial Intelligence&quot;); etc. If you&#x27;re not asking those questions then you&#x27;re holding it wrong.
评论 #16330989 未加载
评论 #16330057 未加载
bryanrasmussen超过 7 年前
How to make background to a picture that is geeky for geeky subjects in 10 minutes:<p>1. find javascript file that has been compressed on your system. 2. open in color coded editor 3. take screenshot<p>there you go, perfect &#x27;code&#x27; background for your deep learning article!
ReverseCold超过 7 年前
I&#x27;m trying to do something similar by starting the other way around (first why it works, then how it works) and so far it&#x27;s working for me pretty well.[1]<p>For reference, I&#x27;m in high school, so I don&#x27;t really have the necessary math background to understand everything first try-but I think I&#x27;ll be able to push through and understand it.<p>The top down (fast.ai) approach didn&#x27;t really work for me - as I felt like I didn&#x27;t really understand how&#x2F;why everything works. Learning the math behind it forces you to understand.<p>[1] <a href="https:&#x2F;&#x2F;nikhiljha.com&#x2F;2018&#x2F;02&#x2F;06&#x2F;Neural-Networks-First-Steps&#x2F;" rel="nofollow">https:&#x2F;&#x2F;nikhiljha.com&#x2F;2018&#x2F;02&#x2F;06&#x2F;Neural-Networks-First-Steps...</a>
mruniverse超过 7 年前
Sounds like a project manager. Step 1) Prepare for project. 1-2 weeks. Step 2) Do programming 3-4 weeks. Step 3) Unit tests and QA 2 weeks.
pixelperfect超过 7 年前
My impression is that a lot of programmers have already followed a similar path, would like to find a job doing ML, but haven&#x27;t found a way to make it happen. Does that sound correct? I&#x27;m not saying the effort isn&#x27;t worth it anyway.
gt_超过 7 年前
How to learn in 3 months:<p>Complete said material in 3 months.
评论 #16322013 未加载