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

Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

docs.google.com

Post reply on HN
Print view View original

21–30 of 123 posts

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#21

Post by kmax12 »

xzzherculeszzx wrote: post #20
kmax12 wrote: post #19

As someone who works with a lot of people new to machine learning, I appreciate guides like this. I especially like the early slides that help frame AI vs ML vs DL so that people can have a realistic understanding of what these technologies are for. For my part, one of the biggest realization I had after many years of applying machine learning was that I got too caught up in the machine learning algorithms themselves…

What are best resources for "defining and generating" labels? Any recommendations?

I don't know of a definitive public resource for this. I published a paper in IEEE's Data Science and Advanced Analytics conference on it back in 2016. You can find that here: https://dai.lids.mit.edu/wp-content/uploads/2017/10/Pred_eng...

Additionally, my company (link in profile) builds a commercial product to help people define and iterate on prediction problems in a structured way based off of the ideas in that paper.

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#24

Post by bllguo »

kmax12 wrote: post #19

As someone who works with a lot of people new to machine learning, I appreciate guides like this. I especially like the early slides that help frame AI vs ML vs DL so that people can have a realistic understanding of what these technologies are for. For my part, one of the biggest realization I had after many years of applying machine learning was that I got too caught up in the machine learning algorithms themselves…

For sure, usually the algorithms aren't the interesting part, but rather how you frame the problem and most importantly what data you have.

I wish I could say I was passionate about feature engineering. I enjoy where deep learning is heading right now - where that kind of finicky, more-art-than-science approach becomes unnecessary, and the model does a better job detecting features than humans.

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#25

Post by mmanfrin »

Good slides, got me back in to the fever of wanting to learn; although a lot of the credit goes to the linked 3Blue1Brown videos (whose Linear Calculus series is excellent) which were a lot more technical but no less approachable.

Question to those versed in ML: I want to work on an AI that plays a video game (aspirations of playing something like Rocket League, but I know I need to start smaller with something like an old NES game). I understand these are usually done with Recurrent Neural Networks, but I'm a little lost as to how to get data in to the RNN -- will I need to make another AI or CNN to read the screen and interpret (including the score?) My 30k ft view is that if I can define a 'score', give it a 'reset' button, and define 'inputs (decision targets)', then I just need to give it the screen and let it do its thing. But getting the 'score' is the part I can't figure out short of adding another layer to the classifier.

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#26

Post by gregorymichael »

candiodari wrote: post #22

Cool presentation ... but there's a million ones like this. We don't need yet another basic introduction to machine learning, we need detailed practical studies of real problems.

Easier to curse the darkness than to light a match.

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#28

Post by npgatech »

rubenfiszel wrote: post #8

If I understand correctly those are slides from a Googler (Not sure if those slides have corporate approval), that probably have as a side goal to showcase that Google is a fun place to do ML. Not that I am judging or anything but, the author's personal website http://www.jasonmayes.com/ whose link is displayed multiple times is a giant ad to get hired elsewhere and show at least some desire for other career opportun…

Checking his website, it reeks of narcissism. There are better ways to assert yourself than to do all the corny things he has done on his self promotion website.

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#29

Post by allenguo »

mmanfrin wrote: post #25

Good slides, got me back in to the fever of wanting to learn; although a lot of the credit goes to the linked 3Blue1Brown videos (whose Linear Calculus series is excellent) which were a lot more technical but no less approachable. Question to those versed in ML: I want to work on an AI that plays a video game (aspirations of playing something like Rocket League, but I know I need to start smaller with something like…

You should check out Berkeley's deep reinforcement learning course[1]. There's lecture videos, slides, and homework assignments, and it's all very up-to-date.

[1] http://rll.berkeley.edu/deeprlcourse/

Re: Machine Learning 101 slidedeck: 2 years of headbanging, so you don't have to

#30

Post by bitL »

kmax12 wrote: post #19

As someone who works with a lot of people new to machine learning, I appreciate guides like this. I especially like the early slides that help frame AI vs ML vs DL so that people can have a realistic understanding of what these technologies are for. For my part, one of the biggest realization I had after many years of applying machine learning was that I got too caught up in the machine learning algorithms themselves…

Deep Learning frees you from the need to do "feature engineering" and usually works much better than methods which require such process. I'd instead recommend everyone to "dive deep" into deep learning and once they master it, get acquainted with classical methods that still might get used here and there. I understand it's difficult to let go of what you worked very hard to understand when you were studying ML, but such is life, "sunk cost fallacy" should not you blind from seeing 95% success rate of DL while observing paltry 60% success rate with SVM/HMM on the same problem. Just let it go.
Post reply on HN