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

It Takes Two Neurons to Ride a Bicycle (2004)

paradise.caltech.edu

Post reply on HN
Print view View original

31–40 of 90 posts

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#31

Post by chestervonwinch »

lucb1e wrote: post #20
chrischen wrote: post #12

I wish math notation becomes substitued with pseudocode. I can never figure out all the greek letters!

But then it wouldn't look as "scientific" (i.e. anyone could understand it, it wouldn't look complicated). At least that's what I feel like, reading and writing a bunch of papers for my master's. We are encouraged to put math stuff in ours just because it looks more theoretical that way. Whenever I do something of worth I also make sure to blog about it so I can write down in normal terms what we did and found, with…

1) Sometimes it's actually helpful to use greek letters when a convention is used. For example: capitals for matrices (A), lowercase for column vectors (a), and Greek for scalars (α).

2) I agree with the gist of your point, but I'm guessing you're being down-voted because you come off as sort of flippant. Anyhow, I've long thought that mathematics should have hover-text to help remove the mental overhead of translating the concise notation to meaningful interpretation. Obviously, using variables names like `velocity_of_thing` is much too verbose in mathematics (papers would 1000's of pages); however, β with hover-text "This is the velocity vector of the thing." would be super helpful IMO.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#32

Post by grawprog »

lucb1e wrote: post #20
chrischen wrote: post #12

I wish math notation becomes substitued with pseudocode. I can never figure out all the greek letters!

But then it wouldn't look as "scientific" (i.e. anyone could understand it, it wouldn't look complicated). At least that's what I feel like, reading and writing a bunch of papers for my master's. We are encouraged to put math stuff in ours just because it looks more theoretical that way. Whenever I do something of worth I also make sure to blog about it so I can write down in normal terms what we did and found, with…

Ya science has this way with needing to look and seem self important. Or at least the scientists reviewing journals.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#34

Post by robotresearcher »

lucb1e wrote: post #20
chrischen wrote: post #12

I wish math notation becomes substitued with pseudocode. I can never figure out all the greek letters!

But then it wouldn't look as "scientific" (i.e. anyone could understand it, it wouldn't look complicated). At least that's what I feel like, reading and writing a bunch of papers for my master's. We are encouraged to put math stuff in ours just because it looks more theoretical that way. Whenever I do something of worth I also make sure to blog about it so I can write down in normal terms what we did and found, with…

> We are encouraged to put math stuff in ours just because it looks more theoretical that way.

If that's really true, you are getting bad advice.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#35

Post by Filligree »

andars wrote: post #25
crispyambulance wrote: post #24

Earlier quoted context omitted.

I guess you can think of it as a "self-tuning" PID controller. It "learns" how to ride a bike. If it were really "just" a PID, you would need some arbitrarily complex procedure involving a human for tuning all the parameters?

It isn't self-tuning, and it doesn't "learn." From the paper: "The three constants c_i need to be set by the implementor" Under "Future Directions": "One obvious thing to do with this system is to have it learn and tune its parameters with experience." The work presented in the paper does not do this . "This network was designed in an ad-hoc, if traditional, way. First, a human tried to control the bicycle with the s…

So it's a PD controller.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#36

Post by Filligree »

Seden wrote: post #15
hathawsh wrote: post #8

Does a Raspberry Pi have enough computing power to run these two neurons in the real world? Could I attach motors and sensors to a real bike and have it drive itself? That would be amazing.

This is just a PID controller, they have existed and been used in industry much longer than computers and thus require almost no computing power at all. Everyone taking higher level engineering courses learns how to design these because almost everything uses them. Honestly I thought that the paper was a joke on how everything is called neural network, but maybe it is serious... https://en.wikipedia.org/wiki/PID_cont…

Funnily, I learned about PID controllers first while playing a Minecraft mod... but yeah, this definitely looks like one.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#37

Post by _dps »

crispyambulance wrote: post #24
tgb wrote: post #17

Earlier quoted context omitted.

Yeah, that was my thinking: how is this doing anything other than a PID controller? Glancing at the paper it actually looked like a PD controller, but maybe I missed some feed back where it could accumulate an integral term as well.

I guess you can think of it as a "self-tuning" PID controller. It "learns" how to ride a bike. If it were really "just" a PID, you would need some arbitrarily complex procedure involving a human for tuning all the parameters?

There's a whole body of theory on Adaptive Control (what the control systems community has called what we would now called "learning based control").

This is one of the classic texts: https://www.amazon.com/Adaptive-Control-Karl-Johan-Astrom/dp...

In short, many techniques that look a lot like modern machine learning have been in use for decades in control theory for tasks exactly like you describe (e.g. automatic tuning of PIDs). If you want to dig into this a bit deeper you might look up the "MIT Rule", which is a gradient style approach for dynamically tuning (and re-tuning) adaptive control systems, and is fairly common for PID tuning.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#38

Post by khedoros1 »

iovrthoughtthis wrote: post #16
Seden wrote: post #15

Earlier quoted context omitted.

This is just a PID controller, they have existed and been used in industry much longer than computers and thus require almost no computing power at all. Everyone taking higher level engineering courses learns how to design these because almost everything uses them. Honestly I thought that the paper was a joke on how everything is called neural network, but maybe it is serious... https://en.wikipedia.org/wiki/PID_cont…

I'm with you here. Did no-one else do robotics in CS?

I did as an undergrad, but I had to petition to take the class because it was considered graduate-level.

Re: It Takes Two Neurons to Ride a Bicycle (2004)

#40

Post by AnsemWise »

Safyia wrote: post #21
lucb1e wrote: post #20

Earlier quoted context omitted.

But then it wouldn't look as "scientific" (i.e. anyone could understand it, it wouldn't look complicated). At least that's what I feel like, reading and writing a bunch of papers for my master's. We are encouraged to put math stuff in ours just because it looks more theoretical that way. Whenever I do something of worth I also make sure to blog about it so I can write down in normal terms what we did and found, with…

It would be great to have a website where the writers of the paper, or well, anyone who understood it well, would write an article about it in a more accessible way with some examples included etc. I am a big fan of blogs explaining such things.

Checkout https://blog.acolyer.org/
Post reply on HN