Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Stanford A.I. Courses

ai.stanford.edu

Post reply on HN
Print view View original

71–80 of 81 posts

Re: Stanford A.I. Courses

#71

Post by Exuma »

mellavora wrote: post #57
Exuma wrote: post #26

Care to explain cross entropy simply? That’s where I paused currently

Shooting from the hip: entropy of a single signal, say a sequence of letters, "ababababab" is the scaled "average" surprise per letter. So if they are uniformly distributed, each letter is equally likely/unlikely to come next in the sequence, where if instead one letter only 1/1000th of the time (aaa....aaa...aa..a.z.aaaa), then when the rare beast shows up, it is a big surprise, so the total amount of surprise avail…

Awesome, thank you very much. Great answer

Re: Stanford A.I. Courses

#72

Post by samstave »

rahimnathwani wrote: post #45
samstave wrote: post #39

Earlier quoted context omitted.

This might be taboo, but I used ChatGPT to educate me on some basic concepts, then deeper concepts - and put together a learning-plan and a syllabus for me with also a glossary of terms.... The cool thing, is it helped me put a more structured thought process on how I should pursuing AI leanings... I couldnt find anything concise out there - and this helped me to better think through everything: If anything - its a g…

The link fails for me. I see a red banner saying: Unable to load conversation 7a36b5dc-0016-4b4c-bf1a-c3a66dac7c6d

I think you have to be logged in it seems, as when I click in private, it asks for login first :-/

Re: Stanford A.I. Courses

#73

Post by rahimnathwani »

samstave wrote: post #72
rahimnathwani wrote: post #45

Earlier quoted context omitted.

The link fails for me. I see a red banner saying: Unable to load conversation 7a36b5dc-0016-4b4c-bf1a-c3a66dac7c6d

I think you have to be logged in it seems, as when I click in private, it asks for login first :-/

I'm logged in.

Did you click the 'share' link on the left (which generates a public URL for a snapshot of the chat), or did you just copy the URL from the address bar (which will only work for you)?

The shareable URLs contain the word 'share' in the path.

Re: Stanford A.I. Courses

#74

Post by samstave »

rahimnathwani wrote: post #73
samstave wrote: post #72

Earlier quoted context omitted.

I think you have to be logged in it seems, as when I click in private, it asks for login first :-/

I'm logged in. Did you click the 'share' link on the left (which generates a public URL for a snapshot of the chat), or did you just copy the URL from the address bar (which will only work for you)? The shareable URLs contain the word 'share' in the path.

huh - I DID click share - lemme try again ;

https://chat.openai.com/share/b8f06d5e-f2d9-47d7-9c60-69b088...

AH... I fd up and apprently copied the URL...

EDIT,

You may link this link as well

https://chat.openai.com/share/0e2d652e-09a6-4cba-a766-dcf2c6...

Re: Stanford A.I. Courses

#75

Post by leminimal »

jph00 wrote: post #51
leminimal wrote: post #6

Are there project-based tutorial that talks more about neural net architecture, hyperparameters selection and debugging? Something that walks through getting poor results and make explicit the reasoning for tweaking? When I try to use transformers or any AI thing on a toy problem I come up with, it never works. Even Fizz-Buzz which I thought was easy doesn't work (because division or modulo is apparently hard to repr…

Yes. I created a course which uses implementing Stable Diffusion from scratch as the project, and goes through lots of architecture choices, hyperparam selection, and debugging. (But note that this isn't something that's fast or easy to learn - it'll take around a month full-time intensive study.) https://course.fast.ai/Lessons/part2.html

Thanks for making that course. It was on my list of courses to look at since GPT-4 recommended it (with all the caveat that entails :) ). Thanks for also making notebooks available alongside the videos.

However, can you point me to the lectures where training happen (and architecture choices, hyperparam selection, and debugging happens.). I'm less familiar with SD but at a quick glance it seems like we're using a pretrained model and implementing bits that will eventually be useful for training but not training a new model, at least in the beginning of the deep dive notebook and first few lessons (starting at part 2, lesson 9).

Re: Stanford A.I. Courses

#76

Post by m3affan »

tonmoy wrote: post #12
ripvanwinkle wrote: post #9

Looking for guidance here. There are a lot of courses out there on AI from esteemed institutions at that. What do people recommend as a curriculum for someone with a formal univ education in CS albeit from a while ago and who has programmed extensively though not in Python. The goal at the end is to have a deep understanding of the LLM space and its adjacencies.

Although I myself am not related to the industry or academia pertaining to AI, I have heard many people speak highly of the zero to hero course by Andrej Karpathy: https://youtube.com/playlist?list=PLAqhIrjkxbuWI23v9cThsA9Gv... I myself loved it and learned a lot, but YMMV

Karpathy is great researcher in the field, but that doesn't always translate into good explanation skills automatically.

Re: Stanford A.I. Courses

#77

Post by vGPU »

mhh__ wrote: post #47
godelski wrote: post #42

Earlier quoted context omitted.

I think this is because of a misalignment that is even common in plenty of other subjects as well. You know how once you've gained expertise in something that it is difficult to explain because it is so obvious? Kinda what is happening in education. Let me explain. The reason a lot of the theoretical basis is taught is because you need to get the skills to learn why things work, when to use them, when they fail, when…

The people with experience also aren't necessarily the ones that end up teaching - which isn't to say the same information can't be conveyed necessarily (e.g. good academics keep up to date with the field in industry) but there is powerful focus that practical experimentation brings.

The ones with experience are most often not the ones teaching. You know what they say, those who can’t do… teach.

Re: Stanford A.I. Courses

#78

Post by mhh__ »

vGPU wrote: post #77
mhh__ wrote: post #47

Earlier quoted context omitted.

The people with experience also aren't necessarily the ones that end up teaching - which isn't to say the same information can't be conveyed necessarily (e.g. good academics keep up to date with the field in industry) but there is powerful focus that practical experimentation brings.

The ones with experience are most often not the ones teaching. You know what they say, those who can’t do… teach.

Some people like to teach

Re: Stanford A.I. Courses

#79

Post by itissid »

wodenokoto wrote: post #56
itissid wrote: post #14

I think the way courses are taught can give you some needed grounding, like you should always take a good linear regression class. But I think that is as far as it gets you, a theoretical base. Honestly the issue is that most ML programs are taught as being some kind of additive skill set: the more courses you take the better or selection of the right kind of courses gets you some where. In reality: 1. most real worl…

> like you should always take a good linear regression class. Any recommendations for a _good_ linear regression class / course?

The only one I know of is Andrew gelmans class in Social sciences dept at Columbia University https://polisci.columbia.edu/content/quantitative-methods-ii...

There are other people in that department like Ben Goodrich who are also good at teaching bayesian statistics

Re: Stanford A.I. Courses

#80

Post by vGPU »

mhh__ wrote: post #78
vGPU wrote: post #77

Earlier quoted context omitted.

The ones with experience are most often not the ones teaching. You know what they say, those who can’t do… teach.

Some people like to teach

I know. I love to teach too. But I’d never take it up as a profession. The vast majority of successful people who have a yearning to pass on their knowledge hand select a few protégés or write a book.

I have had one teacher who was like that. He’d been involved in the development of nuclear weapons before he retired. Incredibly smart guy. Unfortunately, he couldn’t teach physics worth a dime. He had the highest drop out rate of any physics teacher at my college.

Those two scenarios cover the vast majority of cases.

Post reply on HN