Machine Learning Crash Course • Hacker News Board

Re: Machine Learning Crash Course

#221

Post by mixmastamyk » Fri, Mar 02, 2018, 10:02 PM UTC

BadCookie wrote: post #63

3pt14159 wrote: post #23

Earlier quoted context omitted.

Unless you work for a company obviously known for their ML the "expertise" out there right now is brutal. People are building recommendation engines without knowing the very, very, very basics like Jaccard indexes, ROC Curves, or topic drift. I've even had to explain type two error to someone working on one of these before. I agree with your general thrust, and you're right, messy data is often 95% of the problem, bu…

I took a machine learning graduate-level course from Andrew Ng himself, and I don't recall learning about Jaccard indexes or topic drift. Maybe your sense of what counts as "very, very, very basic" is skewed toward your own experience. There's a phenomenon known to psychologists where people tend to think that the stuff that they know is very easy and basic, so they conclude that anybody who doesn't know what they kn…

Oh, wish I knew the name of that phenomenon as well.

Re: Machine Learning Crash Course

#222

Post by wepple » Fri, Mar 02, 2018, 11:21 PM UTC

randcraw wrote: post #122

bjourne wrote: post #53

I want to ask people who know ML well if the hype is warranted? Billions of courses, web sites, job applications and HN posts. The subject seem to have taken off massively in the last two years. I mean image and speech recognition is pretty cool (when it works!), but hardly that earth shattering, is it?

Deep nets are deservedly big because they've managed to improve upon most of the decades-old state-of-the-art methods in the world of signal processing (DSP): voice, image, video, game play, and a significant amount of natural language. No other single computational/algorithmic method has achieved so much in so many domains, ever. That's revolutionary. The rate of advance using deep nets in signal processing will lik…

This is a really fantastic and interesting look at ML, for someone who’s just beginning first steps. Any recommendations on where else I can read about the areas DNNs and associated stuff (GANs, RL, etc) in terms of what they’ll likely not be capable of in the near mid term?

Re: Machine Learning Crash Course

#223

Post by tostitos1979 » Sat, Mar 03, 2018, 12:15 AM UTC

mrdmnd wrote: post #11

As someone who just did this internally: Do it. It's worth your time. Very well paced exercises, and it walks you through the flow quite nicely.

I went through the first a couple of topics. It seemed very disjointed. Different people presenting, different exercises. Was it like this internally? Or is this heavily "annotated"?

Re: Machine Learning Crash Course

#224

Post by sannee » Sat, Mar 03, 2018, 8:20 AM UTC

infinite8s wrote: post #215

gchadwick wrote: post #196

Earlier quoted context omitted.

> It is also absolutely true, in my experience, that you need a graduate-level education or years of hands-on experience to troubleshoot cases where AI/ML fails on a deceptively-simple problem, or to tweak an AI/ML algorithm (or develop a new one) so it can solve a novel problem. How much of that is critical domain specific knowledge and how much of that is just general engineering debugging/problem solving experienc…

The knack for maths is the important bit.

The math necessary for ML/AI (statistics/vector calculus) is mostly taught at undergrad level though isn't it? So most engineers should already have it covered.

Re: Machine Learning Crash Course

#225

Post by epsilon_machine » Sat, Mar 03, 2018, 9:57 AM UTC

stochastic_monk wrote: post #49

fwdpropaganda wrote: post #28

Earlier quoted context omitted.

What's topic drift?

It seems to be a specialized term referring to the change in focus of blogs [0] and online communities [1] over time. This strikes me as a very specialized concept, rather than a generally-important term in machine learning as a whole. Edit: To add my perspective, with years of industry experience and graduate-level machine learning coursework, I have never before encountered this term. [0]: https://link.springer.com…

Also seems closely related to the concept of stationarity in time series analysis [https://en.wikipedia.org/wiki/Stationary_process]

Re: Machine Learning Crash Course

#226

Post by aaron987 » Sat, Mar 03, 2018, 11:31 AM UTC

BadCookie wrote: post #63

3pt14159 wrote: post #23

Earlier quoted context omitted.

Unless you work for a company obviously known for their ML the "expertise" out there right now is brutal. People are building recommendation engines without knowing the very, very, very basics like Jaccard indexes, ROC Curves, or topic drift. I've even had to explain type two error to someone working on one of these before. I agree with your general thrust, and you're right, messy data is often 95% of the problem, bu…

I took a machine learning graduate-level course from Andrew Ng himself, and I don't recall learning about Jaccard indexes or topic drift. Maybe your sense of what counts as "very, very, very basic" is skewed toward your own experience. There's a phenomenon known to psychologists where people tend to think that the stuff that they know is very easy and basic, so they conclude that anybody who doesn't know what they kn…

Are you referring to the Curse of Knowledge?

https://en.wikipedia.org/wiki/Curse_of_knowledge

What you are describing also sounds a little like the Dunning-Kruger effect:

https://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect

Re: Machine Learning Crash Course

#227

Post by stealthcat » Sat, Mar 03, 2018, 12:18 PM UTC

akmiller wrote: post #88

cowmoo728 wrote: post #51

Earlier quoted context omitted.

We have to separate AI researcher and implementation engineer. These types of crash courses help get you to the point where you can reasonably work under PhD level people and write code to test, scale, and deploy their ideas. For many current applications of ML this is acceptable because you're just stealing an idea from a paper or stealing ImageNet to recognize your problem. For anything else you really need to pay…

Exactly. Somewhat akin to graphics programming. There are much smaller groups that work on actually building 3D graphics engines, however, many developers take those engines and use them to build successful applications and games.

So we need to wait for Unity of ML? With Asset Store selling models and datasets.

Re: Machine Learning Crash Course

#228

Post by mlevental » Sat, Mar 03, 2018, 5:35 PM UTC

eddieplan9 wrote: post #3

For those interested in a deeper dive to just deep learning, "Tensorflow and deep learning - without a PhD" is really good, and covers a lot of material in a single 2hr talk. https://www.youtube.com/watch?v=vq2nnJ4g6N0

the deep nets and conv nets stuff was excellent. i wish the explanation of rnns was a little better.

Re: Machine Learning Crash Course

#229

Post by swyx » Sun, Mar 04, 2018, 9:43 PM UTC

Choco31415 wrote: post #213

swyx wrote: post #151

Earlier quoted context omitted.

i completed the andrew ng course recently, and felt that the difficulty dropped a lot in the second half of the course (for example, he stops giving homeworks). im hoping for more in his new DL courses

I've taken the CNN and RNN (parts 4 and 5) classes of his new DL specialization, and they both area about as rigorous as you wanted. I do have to give a warning though that the last class starts so see some confusing mistakes in the HW. For example, the expected output given is from an outdated HW version.

sigh. well i hope the support is good.

Re: Machine Learning Crash Course

#230

Post by sacado2 » Mon, Mar 05, 2018, 4:24 PM UTC

3pt14159 wrote: post #23

minimaxir wrote: post #12

Looking through the topics covered, the standard AI-course caveats ( https://news.ycombinator.com/item?id=16247629 ) apply. Yes, AI/ML MOOCs teach the corresponding tools well, and the creation of new tools like Keras make the field much more accessible. The obsolete gatekeeping by the AI/ML elites who say "you can't use AI/ML unless you have a PhD/5 years research experience" is one of the things I really hate about…

Unless you work for a company obviously known for their ML the "expertise" out there right now is brutal. People are building recommendation engines without knowing the very, very, very basics like Jaccard indexes, ROC Curves, or topic drift. I've even had to explain type two error to someone working on one of these before. I agree with your general thrust, and you're right, messy data is often 95% of the problem, bu…

My ML model is 99.7% sure you're a gatekeeper. Might be a type 1 error, though.