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

What’s the difference between statistics and machine learning?

thestatsgeek.com

Post reply on HN
Print view View original

91–95 of 95 posts

Re: What’s the difference between statistics and machine learning?

#91

Post by hadsed »

dorgo wrote: post #86
Retric wrote: post #80

Earlier quoted context omitted.

The NN complexity is not a question of doing the calculations. Go on a 5x5 board would be a very straightforward game, go in a 19x19 board is not. Similarly, understanding how NN fiction at a nuts and bolts level stops being enough as you build larger networks.

> Go on a 5x5 board would be a very straightforward game I think it is not a good comparison. A small board calls for simpler algorithms: just try out all possible games and choose the most favorable one. For larger boards this simple approach doesn't work any more and you start looking for something different. But the architecture of NN networks doesn't change at all if you move from small to large scales. Only the…

The architecture doesn't change but the way it works often changes dramatically with scale.

Re: What’s the difference between statistics and machine learning?

#92

Post by sweeneyrod »

Retric wrote: post #80
sweeneyrod wrote: post #78

Earlier quoted context omitted.

> Understanding modern ML algebra is really "general relativity hard" if not actually harder. Spiking NNs are "quantum physics hard". The math is very much translatable between these domains. That's not my experience at all. What kind of ML requires something beyond basic linear algebra? Being comfortable manipulating matrices is certainly harder than plugging data into an sklearn function, but it's also significantl…

The NN complexity is not a question of doing the calculations. Go on a 5x5 board would be a very straightforward game, go in a 19x19 board is not. Similarly, understanding how NN fiction at a nuts and bolts level stops being enough as you build larger networks.

But isn't the main theme of NNs that the low level understanding is the best we have? In other words, there is no body of theory we can use to analyse architectural decisions so we just have to go off experimentation and heuristics derived from that.

Re: What’s the difference between statistics and machine learning?

#93

Post by Retric »

sweeneyrod wrote: post #92
Retric wrote: post #80

Earlier quoted context omitted.

The NN complexity is not a question of doing the calculations. Go on a 5x5 board would be a very straightforward game, go in a 19x19 board is not. Similarly, understanding how NN fiction at a nuts and bolts level stops being enough as you build larger networks.

But isn't the main theme of NNs that the low level understanding is the best we have? In other words, there is no body of theory we can use to analyse architectural decisions so we just have to go off experimentation and heuristics derived from that.

I think a huge number of people publishing on the field would disagree with that assessment. Which is not to say they are right, but what looks like oversimplification is rarely accurate.

Re: What’s the difference between statistics and machine learning?

#94

Post by ianamartin »

AstralStorm wrote: post #62
ianamartin wrote: post #38

The difference is in how the output is evaluated. An ML model is evaluated empirically. You compare to real world results and get an accuracy measure. An ML models tells you what something should be. And if it’s a good model, you will get a pretty high frequency of that model telling you what the thing is. Statistics does something entirely different. It tells you what something could be. If you flip a coin, an ML mo…

No, ML model is not evaluated empirically at all. Measures like accuracy and precision are not empirical. Neither is generalization as evaluated by using some model data set. These measures are statistical predictions that may or may not be correct. Failure rate in the wild is empirical. Accuracy in the wild, the same. Since the designer does not have access to real data, they are actually not working empirically at…

You know that data scientists have access to real data, right? It's not all just kids doing tricks on kaggle? That we have the ability to actually measure shit?

Do you think that all of this is a total joke? I mean, you're allowed to think that. But, umm, yeah. Real people do real things with real data. Believe it or not.

Post reply on HN