Machine Learning Crash Course • Hacker News Board

Re: Machine Learning Crash Course

#101

Post by jerf » Thu, Mar 01, 2018, 10:11 PM UTC

gmac wrote: post #83

blackrock wrote: post #60

Earlier quoted context omitted.

What's a "type two" error? I had to google it. It's a false negative. A "Type 1" error, is a false positive. Is this like how people overuse the term "orthogonal"?

"Type I" and "Type II" errors are some of the stupidest and most obfuscatory academic terminology ever invented, and (as an academic) I absolutely refuse to make the effort to learn which way round they go. Just call the bloody things what they are: false positives and false negatives. (Getting seriously OT now, but Kahneman does something annoyingly similar with his talk of "System 1" and "System 2" in Thinking Fast…

As a computer scientist/programmer, there are three numbers, 0, 1, and infinity. If you're going to index your errors by the natural numbers, and you've got Type 1 Errors and Type 2 Errors, my next question is what a Type 3 Error is, and you know what my next question after that is.

Otherwise, please take this wisdom from programmers, who deal with this sort of thing all the time, and use an enumeration, in this case, {False Positive, False Negative} will do just fine.

Re: Machine Learning Crash Course

#102

Post by p1esk » Thu, Mar 01, 2018, 10:24 PM UTC

icc97 wrote: post #48

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…

I fully agree with you that after a MOOC you've barely scratched the surface and until you're implementing them yourself then you're not going to jump into a ML job. However personally I view the rest of the opposite way round. Getting through a course on Deep Learning takes months [0]. Then reading through Keras code once you understand the appropriate NNs is easy. For example it takes a while of going through Neura…

Understanding NNs is easy. Understanding, collecting, and cleaning up data is the hard part.

Also, DL != ML.

Paraphrasing "The Tao of Network Protocols": If all you see is DL, you see nothing.

Re: Machine Learning Crash Course

#103

Post by RealCasually » Thu, Mar 01, 2018, 10:26 PM UTC

lugg wrote: post #100

achompas wrote: post #59

Earlier quoted context omitted.

> 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 the industry. It is absolutely true that you do not need a graduate degree to apply AI/ML to vanilla problems. It is also absolutely true, in my experience, that you need a graduate-level education or years of hands-on experience to troubleshoot cases…

What's an example of a problem that needs that troubleshooting? (Curious)

Fairness and fighting adversarial examples come to mind.

Re: Machine Learning Crash Course

#104

Post by DiogoMCampos » Thu, Mar 01, 2018, 10:26 PM UTC

How does this compare to the CS229 lectures by Andrew Ng? (the recorded lectures, not the MOOC)

Re: Machine Learning Crash Course

#105

Post by eanzenberg » Thu, Mar 01, 2018, 10:27 PM UTC

xamuel wrote: post #73

eanzenberg wrote: post #66

Earlier quoted context omitted.

Why? Most of that cruft is abstracted away, computation only gets cheaper over time (a world class AI rig cost ~30k, a decent one for 2k) and most applications of ML run on commodity hardware.

For one thing, it suggests that they are actually technicians, not the scientists they're selling themselves as. That's fine if you want a technician (and if they're charging technician's rates).

And then that technician rate is X times what a technician rate would be for pure software dev.. what is your point?

Re: Machine Learning Crash Course

#106

Post by achompas » Thu, Mar 01, 2018, 10:27 PM UTC

lugg wrote: post #100

achompas wrote: post #59

Earlier quoted context omitted.

> 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 the industry. It is absolutely true that you do not need a graduate degree to apply AI/ML to vanilla problems. It is also absolutely true, in my experience, that you need a graduate-level education or years of hands-on experience to troubleshoot cases…

What's an example of a problem that needs that troubleshooting? (Curious)

Honestly? The exact problem I'm dealing with at work right now.

We're trying to re-write our recommender for artist music stations at iHeartRadio (aka "I'll listen to Drake or Kendrick Lamar's station at the gym today"). Just today, I tried adding negative sampling to the matrix I'm factorizing, hoping it encourages spread in the embeddings learned for artists in certain types of genres.

I have a MS, but not a lot of research experience. It would have taken me a while to find this solution on my own. However, the moment I described this problem to my manager - a PhD graduate with several years of research and industry experience - he immediately suggested negative sampling.

What I learned during my MS helped me grok the math immediately. We're adding noise to the training set and penalizing vectors lengths to avoid overfitting. Easy! Identifying a solution worth exploring? Not easy, at least without a degree or significant experience.

(There's also the chance I should know this, in which case I have some reading to do. ¯\_(ツ)_/¯)

Re: Machine Learning Crash Course

#107

Post by istorical » Thu, Mar 01, 2018, 10:28 PM UTC

xamuel wrote: post #64

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…

The other day I met with someone who was visiting my city to attend a big ML conference. In the course of our discussion, it transpired this person did not know the Halting Problem. He'd "heard of" Turing machines, but nothing more than "hearing" of them. Gatekeepers shouldn't keep gates just for gatekeeping sake. But if so-called ML experts don't even know undergraduate computer science, that should really give you…

How does knowing that it's impossible to predict whether an infinite loop exists in a piece of code yield an actionable piece of wisdom that this ML expert should have?

I'd suppose that most developers, formal education or not, would have encountered an infinite loop at some point in their initial work with iteration or recursion.

How does knowing that Turing proved you can't predict this bug in a piece of code change anything?

I might genuinely be missing something important here - not trying to be snarky in my questioning.

It seems like obviously infinite loops are a disastrous bug for critical code - but what does knowing the formal name of the problem and background of its discovery give you?

I could understand if you were arguing in favor of test code or static analysis.

Re: Machine Learning Crash Course

#108

Post by loreteye » Thu, Mar 01, 2018, 10:28 PM UTC

My friend partner was out dating his friend at work and he needed an hacker to help spy her device. He got (Roccoshadow (at) gmx (.) com) to help spy her iPhone,facebook,email,whatsapp,calls,skype and others.They literally helped him and now he have her whatsapp Spyed without her noticing.

Re: Machine Learning Crash Course

#109

Post by fibores » Thu, Mar 01, 2018, 10:29 PM UTC

gmac wrote: post #83

blackrock wrote: post #60

Earlier quoted context omitted.

What's a "type two" error? I had to google it. It's a false negative. A "Type 1" error, is a false positive. Is this like how people overuse the term "orthogonal"?

"Type I" and "Type II" errors are some of the stupidest and most obfuscatory academic terminology ever invented, and (as an academic) I absolutely refuse to make the effort to learn which way round they go. Just call the bloody things what they are: false positives and false negatives. (Getting seriously OT now, but Kahneman does something annoyingly similar with his talk of "System 1" and "System 2" in Thinking Fast…

What are some synonyms to Kahneman's System 1 and System 2 then? Because Type 1 and 2 errors seem to be completely equivalent to false and positive negatives. I think Kahneman motivates his decision to introduce the terms System 1 and 2 quite well in his book, and I don't know of any direct counterparts.

Re: Machine Learning Crash Course

#110

Post by aoki » Thu, Mar 01, 2018, 10:31 PM UTC

graycat wrote: post #24

In the course, in lecture "Reducing Loss: Gradient Descent" is "Convex problems have only one minimum; that is, only one place where the slope is exactly 0. That minimum is where the loss function converges." The first sentence is flatly wrong: E.g., for positive integer n and the set of real numbers R, function f: R^n --> R where for all x in R^n f(x) = 0, f is convex, concave, and linear, and for all x in R^n x is…

i would request that you stop critiquing "machine learning" based on the presentation in introductory online materials like this and the ng coursera course. you provide a lot of signal in general but i think these critiques do decrease your SNR.

i am certain that you are familiar with the "usual" statistics sequence. (for others: there are lower-division courses that use calculus in a few places but otherwise avoid it, focusing instead on memorizing procedures. there is the upper-division probability/math stat sequence that uses calculus heavily but avoids analysis. and there is an intro phd sequence that finally gets into measure theory.) if you look at a coursera course that gives an high-level overview of practical statistics and simplifies its presentation to be accessible to people who never took calculus, you can criticize the very idea of a course that does not explain the measure-theoretic issues, but it makes no sense to use it to criticize the field of statistics, or to criticize the competence of others in the institution that produced it.

here, google is producing introductory training materials for developers. many developers have never taken calculus, let alone optimization, statistics, or analysis, and when i took MLCC internally, you were supposed to go through this whole thing (lectures and coding) in two days. it's supposed to give you enough understanding of the concepts to understand the API and apply it.