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

You might not need machine learning

nullprogram.com

Post reply on HN
Print view View original

91–100 of 201 posts

Re: You might not need machine learning

#91

Post by unishark »

maweki wrote: post #29
lmilcin wrote: post #26

Earlier quoted context omitted.

Well... I guess most people equal ML with AI and use these terms interchangeably. If you just replace ML with AI everywhere in this article it is going to make sense. The article has other problems, one being the main premise. The problem isn't to drive a car around track (which is what the polynomials did) but rather write a program that can figure out how to drive a car without you knowing how to solve it.

That's not symbolic AI though. That's only statistical methods. The statistical methods are all the rage now, but explainable AI that can reason is an important area of computer science (and research) and uses formal methods. Edit: yeah, you can downvote this, but current AI research splits right along this line, whether it's symbolic or statistical. Some AI courses will use NNs, others will use Prolog and ASP. You c…

"Expert systems" were the hot research area in AI prior to machine learning (data driven methods, basically). Old methods and problems from that era like automated reasoning still have some research and applications going on, but aren't remotely as big an area as machine learning.

Re: You might not need machine learning

#92

Post by dr_dshiv »

karolkozub wrote: post #20

I love the article, but I don't agree with the premise that machine learning equals neural nets. In my understanding machine learning is a very broad term that just as well could be applied to the polynomial model if the constants were optimized algorithmically. I feel like the presented argument is more for transparent vs opaque models rather than machine learning vs something else. Also one could argue that the pol…

As soon as we recognize plain old regression as machine learning, then we start to see "averages" as models of systems and how practically useful could that be?

Re: You might not need machine learning

#93

Post by yalogin »

I understand it’s not needed but is it wrong? I see machine learning as a general purpose black box function approximation tool. It could be a polynomial curve or something else entirely, as long as we have enough data we can approximate it using ML. So in one way I see it as a “lazy man’s easy way out” tool.

Re: You might not need machine learning

#94

Post by johnmoberg »

qayxc wrote: post #90
luc4sdreyer wrote: post #66

Earlier quoted context omitted.

> On top of that you have Elon Musk thinking we are a few months away from SkyNet even though we are decades and decades away from AGI. The actual problem is that we don't know how long it'll be until we build an AGI. Experts put the range somewhere between 10 years and never. Building an unconstrained AGI is an existential risk, so it's important to try and narrow the confidence bands on these questions. That's one…

> 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?

Re: You might not need machine learning

#95

Post by astrea »

All he proved was you don't need a neural network for MicroMouse. We've known that for years. Some problems do require it. In my job experience, facial recognition can't be easily done with traditional signals processing. Stereo vision can be, but the algorithms are slow, expensive, and very error prone when compared to deep learning models.

Re: You might not need machine learning

#96

Post by curiousllama »

The best time series prediction model is often “Use the previous day (or week’s) value”. The best classification model is often “pretend everything is the same.” The best regression model is often “assume it’s the mean”.

This should not be surprising: a core premise of data science (empiricism in general? All logic and human knowledge?) is that intuition is often wrong. Initial hypotheses/problem definitions are just intuition.

Re: You might not need machine learning

#97

Post by username90 »

mjlee wrote: post #18
snemvalts wrote: post #5

The approach they show in the end - it's still machine learning though? Exploring a space and finding parameters to optimize for a loss function (speed around the track), just not deep learning with neural nets.

I think Arthur Samuel would agree. This approach has a loss function, parameters, and inputs that feed in to a model to optimise the parameters. The big difference between this and the other approach mentioned in the article is the model is a simple one that's easy to understand instead of a many layered neural network which is rather opaque. I think the article may be better titled "You might not need neural network…

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. Everything done in this article was known and used before computers existed hence not machine learning.

Doing automatically controlled systems was still possible before computers just that it required a bit more creative use of analog components.

Re: You might not need machine learning

#98

Post by mumblemumble »

maweki wrote: post #27
karolkozub wrote: post #20

I love the article, but I don't agree with the premise that machine learning equals neural nets. In my understanding machine learning is a very broad term that just as well could be applied to the polynomial model if the constants were optimized algorithmically. I feel like the presented argument is more for transparent vs opaque models rather than machine learning vs something else. Also one could argue that the pol…

The machine learning course at my university starts out with polynomial regression and estimators, statistics of classification, etc.. Neural networks are only one tool in a large toolbox. But they are all the rage and it is no surprise that a lot of people want to play with them. Cynically, neural networks are easier as you don't really have to think about your model. Give some examples with some classes and you're…

> Cynically, neural networks are easier as you don't really have to think about your model. Give some examples with some classes and you're done.

This way of thinking about it leads directly to things like statistical redlining.

It's also not specific to neural networks. I take a similar approach with logistic regression. Except that I like to replace the "and you're done" step with, "and you're ready to analyze the parameters to double check that the model is doing what you hope it is." Even when linear models need some help, and I need to do a little feature engineering first, I find that the feature transformations needed to get a good result are generally obvious enough if I actually understand what data I'm using. (Which, if you're doing this at work, is a precondition of getting started, anyway. IMNSHO, doing data science in the absence of domain expertise is professional malpractice.)

There is no, "and you're done" step, outside of Kaggle competitions or school homework. Because machine learning models in production need ongoing maintenance to ensure they're still doing what you think they're doing. See, for example, https://research.google/pubs/pub43146/

Re: You might not need machine learning

#99

Post by sdoering »

mlthoughts2018 wrote: post #78
sdoering wrote: post #16

It is a nice, albeit problematic example. Nonetheless I find many such examples in my daily work as a Data Analyst. Regarding recommender systems I see many companies trying neural nets and so many other fancy ML stuff for things that - in AB-tests are always outperformed by basic rules. I understand the fun it is to build stuff and to use the new hot stuff. And at least for many analysts and marketing people as well…

> “ Regarding recommender systems I see many companies trying neural nets and so many other fancy ML stuff for things that - in AB-tests are always outperformed by basic rules.” I work on large scale recommender systems for an ecommerce company and in my career I’ve seen only the exact opposite. Don’t get me wrong, sometimes simpler ML models, like clustering LSA vectors or nearest neighbors, work better than complex…

From big automotive clients to small-ish fashion eCommerce. From publishing to food-delivery (with upselling in the checkout process) - I found the gains in using rules -> simple ML techniques -> complex systems like NN in most cases not to warrant the costs.

The quality of recommendations nearly always increased from a revenue as well as perceived quality standpoint. However, it almost never had a positive impact on the profit margin that would have justified the necessary investments.

As said - from a quality standpoint most simple systems were just "good enough".

One would need to know the business case and environment. But take automotive (new cars) as an example: The goal is nearly always to get the user to request some form of contact from a physical dealership near them. For that you nearly never need a perfekt, fully configured recommendation.

I know of an example (a car manufacturer) where the search space of all configurable variants (including various things the car owner would never register because they are specific screw variants) is of a size where even the number of visitors to the website per year is some orders of magnitude less than the number of options.

The way to go here was to reduce the search space and the number of variants. Here it turned out that you can, quite fast, reach that goal with few specific questions (active learning) to lead the user to vehicle variants, which correspond to its interests and led to a disproportionately high contact behavior.

And yes: ML techniques were used for the analysis and reduction of the search space. For the concept people to then develop specific questions to get to these reduced attributes. But in the end the recommender now works rule-based.

I don't imply that this holds true for every scale of company/problem. And I know some counter examples - but most companies do not operate on that scale. If you are ebay, Zalando (Germany) and the likes: I would probably get different results from testing the revenue validity of the different approaches.

Re: You might not need machine learning

#100

Post by tyingq »

m463 wrote: post #63
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…

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.

Post reply on HN