Hacker News Reader

Comment by dazhbog | Hacker News Reader

I once went to an antenna tuning/design/factory for my startup's product and I told the guy there, I want an antenna to support X frequencies, this that dBs, good VSWR, hopefully achieve X kilometers range, etc etc.

Two days later he had 3 designs of antennas ready to be made into a flexible PCB and two days after that we got the FPCB samples.

I was amazed so I asked to see how he works. He took copper tape, and with a boxcutter he carves the antenna, and adds solder blobs to tune with the network analyzer. Then, once he was satisfied, he shoved them into the anechoic chamber and boom, done. Black magic stuff.

Antenna intuition is really hard to attain, it takes years playing with the right equipment in the right environment..

View on HN

I remember this from a professor in college as well. I spent weeks modeling an antenna element and then once I had it made, he brought out the copper tape and a knife and tuned it to closer match what we wanted. It is humbling to see this kind of craftsmanship in technology.

I think with good simulation tools, optimization processes, maybe even deep learning, we could make it a lot less of black magic. Make it boring and approachable instead.

It kind of reminds me of chemistry. You have physical laws that are fairly simple but the interactions are hard to describe without a bunch of computation.

What’s the point of applying deep learning to something for which we have an exact mathematical theory?

Answer: because the exact mathematical theory can't give you models, just the performance of a given model.

Calculating EM equations exactly is also a GIGANTIC PAIN IN THE BNC connector.

It's much sexier if you add some deep learning

The analysis part of engineering is, thanks to modern computers, practically "done". However, we are still not able to do synthesis well. We also have exact mathematical models for that, but it usually amounts to NP-hard problems (think integer optimization).

I don't know about this specific case, but often the exact models are so complex that you can't optimize them analytically, so you resort to a global optimization best effort, where the results are not guaranteed to be any good - so you might as well try something DL-based too, to see how it would perform.

Classic traveling salesman problem cast into a large number of analytically incompatible and often hard to quantify dimensions.

>maybe even deep learning, we could make it a lot less of black magic

these two things are antithetical

I'm not sure how useful DL is for optimization, but other techniques such as Genetic Algorithms or Simulated Annealing would make more sense, I think.

Indeed. The evolved antenna page has an example. https://en.wikipedia.org/wiki/Evolved_antenna (previously here: https://news.ycombinator.com/item?id=18449434).

GAs are even more “black magic” than DL

I saw a NASA Tech Brief from 25 years ago where they did that for a small multi-band satellite antenna. The result looked like a pin cushion someone sat on.

It's been done: https://www.researchgate.net/publication/228909002_Automated...

How does slathering deep learning onto something make it less of a black magic?

That's a good point, but given the search space is a set of voxels, you can probably brute force a yuge amount of possibilities and fit some sort of paramterized curve to them.

That's the sort of talk that gets the villagers sharpening their pitchforks.

Well deep learning is just a good way to make universal function approximators. So that's not magic.

I don't how know why neural nets get such a bad rap, they work well for many problems.

> Antenna intuition is really hard to attain

For some reason this reminded me of musician Carolina Eyck playing a theramin on this Tiny Desk Concert:

https://www.npr.org/2019/01/10/683943414/carolina-eyck-and-c...

It’s worth watching to see her demo how she plays the different notes and also changes the volume. And here’s more of a theramin tutorial by her:

https://youtu.be/MJACNHHuGp0

Reply on news.ycombinator.com