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

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

#121

Post by q1bz2p » Fri, Dec 15, 2017, 10:58 PM UTC

cerealbad wrote: post #114

bpizzi wrote: post #112

Earlier quoted context omitted.

That's a strongly pessimistic view you got here. Are you aware that there's people thinking the opposite of you? The thing is: the reality is always far more balanced that what the extremists are preaching us.

is being disagreeable sufficient claim to argument?[0] is there a profit motive in balance?[1] people with vast weapons of control, deception and war shape reality, is it balanced?[2] [0][1][2] no

i have seen a few of your comments and i would like to talk to you further. can you contact me? my email is my username @gmail

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

#122

Post by agibsonccc » Tue, Dec 19, 2017, 10:47 AM UTC

fnl wrote: post #113

agibsonccc wrote: post #103

Earlier quoted context omitted.

A lot of people make money with deep learning with images ;). I guess what I wanted to do was add a bit of nuance. It can help reduce the amount of feature engineering needed. Of course you still need a baseline representation though. More feature engineering also doesn't hurt. I always think of deep learning in the time series context as a neat SVM kernel with some compression built in. With the right tuning it can…

I work with language, not images. There, clever feature engineering isn't just better, it's essential to get anything that is production worthy. In fact, it will even be embedded in some expert system process if your system needs to understand very complex relationships. AI around the corner my ass... :-)

Agreed :). Workflow matters a lot more than the hype Sandhill road and google's marketing team are perpetuating. Good on you for making it work in the real world for something outside of vision/speech!

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

#123

Post by iamwil » Sun, Dec 24, 2017, 5:08 AM UTC

iamwil wrote: post #46

vowelless wrote: post #33

Slide 64: A whole tonne of stuff going on in robotics right now. Just take a look at Boston Dynamics YT channel for some mind bloding research, most of which is driven by ML. . I highly doubt that BD is doing any ML work right now ... Can the author link to specific research that they are doing using ML?

As I remember, they don't use any deep learning ML. I think their stuff is based on something about funnels.

For those interested, I saw the funnel stuff here: https://www.youtube.com/watch?v=7enj1FGoYwg&feature=youtu.be...