You might not need machine learning • Hacker News Board

Re: You might not need machine learning

#151

Post by iakh » Tue, Nov 24, 2020, 6:31 PM UTC

tyingq wrote: post #100

m463 wrote: post #63

Earlier quoted context omitted.

in motorcycles (and rwd cars) everyone knows you steer with the rear anyway.

Somewhat related, it's interesting how non-intuitive steering is to people for motorcycles and bicycles. They do it correctly, but it's hard to reason about. That is, that pushing the left handgrip forward, at speed, turns left and not right. Yet, at very slow speeds, like walking it, it's the opposite.

Thanks for this comment. I used to ride casually but had never heard of this. Found a quick video to explain it

https://youtu.be/ZpV2Bg-WX0w

Re: You might not need machine learning

#152

Post by martamorena9182 » Tue, Nov 24, 2020, 6:46 PM UTC

blackbrokkoli wrote: post #80

stfwn wrote: post #31

> A key feature of neural networks is that the outputs are a nonlinear function of the inputs. However, steering a 2D car is simple enough that a linear function is more than sufficient, and neural networks are unnecessary. This depends entirely on the definition of 'steering a 2D car'. In the model used, throttle is simply proportional to the distance to the nearest wall in front of the car. This means the agent wil…

I see the article more as a broader metaphor for the AI hype. Take, I dunno, video recommendation. Sure, YouTube itself proably built insane stuff in their engine you could never replicate with classic methods (ignoring whether the YT algo is any good). However, if we are just talking about the Vlog of your real estate company, you should probably A/B-test whether your viewers prefer order by time or clicks and imple…

> Sure, YouTube itself proably built insane stuff in their engine you could never replicate with classic methods

Probably. But pretty much anything they recommend is junk, so... That's where the author may have a point. If you don't understand your AI algorithm anymore, it's hard to improve it or even realize how wrong it is. AI is generally good at steering the masses into a couple of "averaged" directions. At the individual level though, it's often crap, unless you are the perfect stereotype that the algorithms assumes you to be.

Re: You might not need machine learning

#153

Post by dryrunes » Tue, Nov 24, 2020, 7:17 PM UTC

username90 wrote: post #121

disgruntledphd2 wrote: post #114

Earlier quoted context omitted.

> Machine learning is a set of techniques developed to attack modeling problems that traditional algorithms couldn't solve. So if the algorithm was developed and used before computers it definitely isn't machine learning I think that it's important to note here that this was the set of problems that computer science researchers didn't know how to solve. In the early days, they mostly ended up re-inventing statistical…

> And to be fair, a neural net is just a bunch of linear models joined by a non-linearity. Nobody did this before computers though. > . In that case, it's essentially stacked logistic regression, which was invented before computers. It isn't "basically logistic regression", it is just a technique which uses logistic regressions. The full technique is ML. If you remove the ML parts it is basically just logistic regres…

Is logistic regression not ml? Or maybe only if it's fit with gd?

Re: You might not need machine learning

#154

Post by qayxc » Tue, Nov 24, 2020, 7:34 PM UTC

johnmoberg wrote: post #94

qayxc wrote: post #90

Earlier quoted context omitted.

> Building an unconstrained AGI is an existential risk But why? So far no-one has been able to explain this to me. An AGI in at of itself is nothing but a brain-in-a-vat. The exponential increase in scientific knowledge was based on the scientific method, which replaced the ancient Greece discussion-based epistemology with a cycle of observation-hypothesis->test->observation->... An isolated AGI cannot test its predi…

Even without physical interaction, you can do a whole lot with just an internet connection. A superintelligence could identify 0-day exploits and quickly spread across thousands of computers and thus render itself immune to your idea of just switching it off. What do we do then? Sure, we can shut down the internet, but where is that going to leave us and how much damage has been done before that happens?

> A superintelligence could identify 0-day exploits and quickly spread across thousands of computers and thus render itself immune to your idea of just switching it off. What do we do then?

How about simply pulling the plug of the computer or even just the network cable?

More to the point, how would an AI even learn about such mysterious exploit if it doesn't have access to an external network in the first place? Even run-of-the-mill supercomputer centres aren't directly connected to the internet for security reasons, so why change that with a potentially dangerous computer program?

Re: You might not need machine learning

#155

Post by disgruntledphd2 » Tue, Nov 24, 2020, 7:35 PM UTC

username90 wrote: post #121

disgruntledphd2 wrote: post #114

Earlier quoted context omitted.

> Machine learning is a set of techniques developed to attack modeling problems that traditional algorithms couldn't solve. So if the algorithm was developed and used before computers it definitely isn't machine learning I think that it's important to note here that this was the set of problems that computer science researchers didn't know how to solve. In the early days, they mostly ended up re-inventing statistical…

> And to be fair, a neural net is just a bunch of linear models joined by a non-linearity. Nobody did this before computers though. > . In that case, it's essentially stacked logistic regression, which was invented before computers. It isn't "basically logistic regression", it is just a technique which uses logistic regressions. The full technique is ML. If you remove the ML parts it is basically just logistic regres…

Like, logistic regression uses a non-linearity to convert the outputs to the 0-1 scale. How does that differ from a one layer neural network?

I think this would probably be a more profitable discussion if you could define Machine Learning for me.

Re: You might not need machine learning

#156

Post by noobermin » Tue, Nov 24, 2020, 7:38 PM UTC

stfwn wrote: post #31

> A key feature of neural networks is that the outputs are a nonlinear function of the inputs. However, steering a 2D car is simple enough that a linear function is more than sufficient, and neural networks are unnecessary. This depends entirely on the definition of 'steering a 2D car'. In the model used, throttle is simply proportional to the distance to the nearest wall in front of the car. This means the agent wil…

That is the point, for some problems NN is unnecessary. That isn't an argument against the point, that is the point. Many problems in life allow simpler models and can save time and computational power if people used their brains first.

Re: You might not need machine learning

#157

Post by disgruntledphd2 » Tue, Nov 24, 2020, 7:38 PM UTC

wokwokwok wrote: post #126

disgruntledphd2 wrote: post #112

Earlier quoted context omitted.

> and we have like 20 years of proof that using hand crafted models has been proven not to scale effectively. What do you mean by this? In what context? Like, the twenty year old models are still running in credit risk and insurance, so I'm confused if you mean in ML/statistical modelling.

You know, driving cars, like the article was talking about? ...or, NLP, audio & image recognition, recommendations... come on. It’s not controversial.

> recommendations

A lot of this is standard statistical methods, much of which are much older than twenty years.

Really, that's the part that threw me, twenty years ago everyone was going crazy for SVM's, which is still machine learning, but the features were definitely hand crafted.

I think deep learning has been super successful with unstructured data, but for tabular data it's pretty much a wash between NN's and boosted trees or generalised additive models.

You do need some flexibility in your function approximation, but not as much as people commonly believe.

Re: You might not need machine learning

#158

Post by disgruntledphd2 » Tue, Nov 24, 2020, 7:39 PM UTC

mattkrause wrote: post #140

wokwokwok wrote: post #126

Earlier quoted context omitted.

You know, driving cars, like the article was talking about? ...or, NLP, audio & image recognition, recommendations... come on. It’s not controversial.

I do sorta wonder about that. The deep learning "revolution" corresponded with an exponential growth in the time/effort/money being thrown at these problems and the amount of data available to do so. In an alternate universe, could everyone be going crazy about kernel machines?

Maybe.

GPU's are definitely a big part of why this stuff has improved, as you can train much, much faster on larger datasets which is going to improve performance.

NN's are super flexible though, and I'm not sure you'd have gotten the same level of performance out of other methods.

Interesting question though.

Re: You might not need machine learning

#159

Post by disgruntledphd2 » Tue, Nov 24, 2020, 7:41 PM UTC

tgv wrote: post #135

disgruntledphd2 wrote: post #116

Earlier quoted context omitted.

Yes, there was. It was just called statistical modelling.

There were no machines in the sense of ML in 1740.

But ML is essentially just function approximation, and that definitely existed back then.

I know this is super pedantic, but it's important to remember the roots of things, and that even things which appear new have precursors that are much older than a lot of people realise.

Re: You might not need machine learning

#160

Post by ummonk » Tue, Nov 24, 2020, 7:43 PM UTC

I'd make two broad points against this article:

A) In most domains, a nonlinear model is far superior to a linear model. At the very least, generally you need to at least apply a transformation (e.g. logistic) to create a nonlinear model from a linear model, because most problem spaces are nonlinear. A nonlinear model doesn't have to be particularly complex though.

B) Machine learning (i.e. automatic tuning of parameters) is far simpler for the user than manual tuning of parameters. It's not a question of whether you "need" machine learning, but whether it will save you work. In fact, the author here is in denial - he actually says he would do machine learning, but doesn't realize that is what it is: "Instead of doing anything fancy, my program generates the coefficients at random to explore the space. If I wanted to generate a good driver for a course, I’d run a few thousand of these and pick the coefficients that complete the course in the shortest time."