Andrej Karpathy 给机器学习初学者的建议-CSDN博客

本文链接：https://blog.csdn.net/baiyu33/article/details/136383827

Andrej Karpathy 给机器学习初学者的建议

请添加图片描述

原文内容

https://www.youtube.com/watch?v=I2ZK3ngNvvI
Advice for machine learning beginners | Andrej Karpathy and Lex Fridman

是一段大约5分钟的访谈视频的精选片段。关于对 ml 初学者的建议。

Lex: You are one of the greatest teachers of machine learning, AI ever from cs231n to today. What advices would you give to beginners interested in getting into machine learning?

给 ml 初学者一点建议？

Andrej: Beginners are often focused on like what to do, and I think the focus should be more like how much you do. So I’m kind of like believer on a high level in this 10 thousand hours concept where you just kind of have to just pick the things whre you can spend time and you care about and you’re interested in, you literally have to put in 10000 hours of work. It doesn’t even like matter as much like where you put it and you’ll iterate and you’ll improve and you’ll waste some time, I don’t know if there’s a better way. You need to put in 10000 hours. But, I think it’s actually really nice because I feel like there’s some sense of determinism about being an export at a thing if you spend ten thousand hours, you can literally pick an arbitrary thing, and I think if you spend 10000 hours of deliberate effort and work, you actually will become an expert at it. And so, I think it’s kind of like a nice thought. And, uh, basically I would focus more on like, “are you spending 10000 hours that’s what I’m focus on”.

我信仰 10000 小时理论。初学者不必纠结 “做什么”，应当关注 “做了多少”。10000小时是说要刻意努力.

Lex: So and then thinking about what kind of machanisms maximize your likelihood of getting to ten thousand hours exactly which for us silly humans means probably forming a daily habit of like every single day actually doing the thing.

对普通人来说， 10000小时后，就会养成习惯，很自然了。

Andrej: Yep, whatever helps you, so I do think to a large extent is a psychological problem for yourself. One other thing that I hope that I think is helpful for the psychology of it is, many times people compare themselves to others in the area. I think this is very harmful. Only compare yourself to you from sometime ago, like say, a year ago, are you better than you year ago. This is the only way to think. And I think this then you can see your progress, and it’s very motivating.

对。并且要注意，在应用10000小时理论时候，要和自己比较，和别人比较对你只有害处。和你的1年前比较，我觉得这是唯一有效方法。

Lex: That’s so interesting that focus on the quantity of hours, because I think a lot of people, uh, in the beginner stage but actually throughout get paralyzed by the choice like which one do I pick, this path or this path. They’ll literally get paralyzed by like which IDE to use.

许多初学者都有选择困难症呢, 比如纠结用哪个 IDE.

Andrej: Well they’re worried about all these things. But the thing is, some of the you, will will waste time doing something wrong. You will eventually figure out it’s not right. You will accumulate scar tissue, and next time you’ll grow stronger, because next time you’ll have the scar tissue and next time you’ll learn from it and now next time you come into a similar situation you’ll be like all right. I messed up. I’ve spent a lot of time working on things that never materialize into anything and I have all that scar tissue and I have some intuitions about what was useful, what wasn’t useful, how things turned out, so all those mistakes were not dead work. So I just think you should just focus on “did you focused on working?”, “what have you done?”, “what have you done last week?”

对，纠结中会选错，后来会发现错误。但每次错误会让你长见识，吸取教训，下次遇到问题就知道结果是怎样的。这些累计的失败，帮我建立了直觉，关于什么是有用的，什么是无用的，这些失败的工作并不都是死工作。我觉得你只需要专注于你所做的事情上，你做了什么，上周做了什么。

Lex: That’s a good question actually to ask for, for a lot of things not just machine learning. It’s a good way to cut the, the I forgot what the term will use but the fluff the blubber whatever the inefficiencies in life. What do you love about teaching. You seem to find yourself often in the like drawn to teaching. You’re very good at it but you’re also drawn to it.

嗯，这对于ml之外的事情也适用。这个方法减少了生活中的低效率。说说你喜欢教学这件事儿？

Andrej: I mean I don’t think I love teaching, I love happy humans, and happy humans like when I teaching. I wouldn’t say I hate teaching, I tolerate teaching, but it’s not like the act of teaching that I like. It’s that I have something I’m actually okay at it, I’m okay at teaching and people appreciate it a lot. And so I’m just happy to try to be helpful, and teaching itself is not like the most, I mean it’s really no it can be really annoying, frustrating I was working on a bunch of lectures just now, I was reminded back to my days of 231n, just how much work it is to create some of these materials and make them good, the amount of iteration and thought and you go down blind alleys and just how much you change it, so, creating something good, in terms of like educational value is really hard, and it’s not fun.

我不是喜欢教学，我是喜欢快乐的人类，我教课的时候人们快乐 / 人们快乐的时候喜欢我上课。

Lex: It’s difficult so for people should definitely go watch your new stuff you put out. there are lectures where you’re actually building the thing like from like you said, the code is truth, so discussing back-propagation by building it, by looking through and just the whole thing, so how difficult is that the prepare for, I think that’s a really powerful way to teach. How did you have to prepare for that, or, are you just live thinking through it?

Andrej: I will typically do like, say, three takes, and then I take like the better take, so I do multiple takes and I take some of the better takes and then I just build out a lecture that way. Sometimes I have to delete 30 minutes of content, because it just went down in alley that I don’t like too much. There’s about a bunch of iteration, and it probably takes me somewhere around 10 hours to create one hour of content.

Lex: It’s interesting I mean is it difficult to go back to like the basics. Do you draw a lot of like wisdom from going back to basics?

Andrej: Yeah, going back to back propagation, loss functions, where they come from, and one thing I like about teaching a lot, honestly, is it definitely strengthens your understanding. So it’s not a purely altruistic activity. It’s a way to learn. If you have to explain something to someone, you realize you have gaps in knowledge. And so I even surprised myself in those lectures like, also the result will obviously look like this, and then the result doesn’t look like it and I’m like “okay I thought I understood this”.

Lex: Yeah, but that’s why it’s really cool to literally code you run it in a notebook, and it gives you a result, and you’re like, “oh wow yes”, and like actual numbers, actual input X, actual code.

Andrej: Yeah, it’s not mathematical symbols, Etc, the source of truth is the code. It’s not slides. It’s just like, let’s build it. It’s beautiful.

Lex: You’re a rare human in that sense.