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

The Alien Style of Deep Learning Generative Design

medium.com

Post reply on HN
Print view View original

11–18 of 18 posts

Re: The Alien Style of Deep Learning Generative Design

#11

Post by chas »

nickpsecurity wrote: post #8
tfgg wrote: post #4

It's not obvious that these designs have anything to do with deep learning; it doesn't appear to be mentioned in any of the linked articles.

I was seriously wondering about the metal one. Let's go link by link. 1. 3D Makeover Link for metal CAD work says nothing about generative techniques. It's about additive manufacturing" letting them do designs like in the photo. 2. The antenna link says it was a generative design by automated search and simulation. Describes Dreamcatcher system that does this with cloud computing. Gives example of roll cage that look…

With the exception of the antennas designed with genetic algorithms[0], the "alien" aesthetic in all of these examples looks like the output of topological optimization tools. For example: https://www.youtube.com/watch?v=igRFFMSfwSQ

They emphasize that Dreamcatcher uses a "top-down" style of design, so maybe they are using deep learning for NLP to parse requirements and then feeding those requirements into normal topological optimization tools?

[0] https://ti.arc.nasa.gov/m/pub-archive/1244h/1244%20(Hornby).... (pictures from their post on page 5)

Re: The Alien Style of Deep Learning Generative Design

#12

Post by nerdponx »

daysforbeef wrote: post #10

Man some of those examples taken from application of genetic algorithms, and iterative algos that are definitely not deep learning ... not everycomputer optimized design success is an AI success and not every AI success is a deep learning success

Why couldn't generative optimization be considered AI? Iteration leading to invention is a common pattern in human intelligence.

Re: The Alien Style of Deep Learning Generative Design

#13

Post by RangerScience »

pierrebai wrote: post #9

One wonders at the unexpected brittleness. Take that bike stem: they describe the automated design process as inputting the forces you wish to withstand and let the algorithm optimize. That implies that the final form has no validation for any other forces. The bike stem might be weak to a diagonal force. I also see that the structural design presented are mostly variation around the simple known trick of triangulati…

These design techniques pretty much require 3d printing for fabrication.

Re: The Alien Style of Deep Learning Generative Design

#14

Post by dogma1138 »

nerdponx wrote: post #12
daysforbeef wrote: post #10

Man some of those examples taken from application of genetic algorithms, and iterative algos that are definitely not deep learning ... not everycomputer optimized design success is an AI success and not every AI success is a deep learning success

Why couldn't generative optimization be considered AI? Iteration leading to invention is a common pattern in human intelligence.

If it's just mutation then no.

Re: The Alien Style of Deep Learning Generative Design

#15

Post by Eridrus »

dogma1138 wrote: post #14
nerdponx wrote: post #12

Earlier quoted context omitted.

Why couldn't generative optimization be considered AI? Iteration leading to invention is a common pattern in human intelligence.

If it's just mutation then no.

And deep learning is just optimization which is just search, which everyone agrees is not AI. /s

Re: The Alien Style of Deep Learning Generative Design

#16

Post by crestedtazo »

dogma1138 wrote: post #14
nerdponx wrote: post #12

Earlier quoted context omitted.

Why couldn't generative optimization be considered AI? Iteration leading to invention is a common pattern in human intelligence.

If it's just mutation then no.

This user rarely contributes to discussions and frequently gives short, useless answers like this.

Can I ask HN why this account hasn't been banned yet? I thought the behavior this user is demonstrating directly violates HN guidelines?

Re: The Alien Style of Deep Learning Generative Design

#17

Post by grzm »

crestedtazo wrote: post #16
dogma1138 wrote: post #14

Earlier quoted context omitted.

If it's just mutation then no.

This user rarely contributes to discussions and frequently gives short, useless answers like this. Can I ask HN why this account hasn't been banned yet? I thought the behavior this user is demonstrating directly violates HN guidelines?

If you have concerns about a member, you can email the mods directly via the Contact link in the footer. This is more effective than commenting on it.

Re: The Alien Style of Deep Learning Generative Design

#18

Post by mattkrause »

chas wrote: post #11
nickpsecurity wrote: post #8

Earlier quoted context omitted.

I was seriously wondering about the metal one. Let's go link by link. 1. 3D Makeover Link for metal CAD work says nothing about generative techniques. It's about additive manufacturing" letting them do designs like in the photo. 2. The antenna link says it was a generative design by automated search and simulation. Describes Dreamcatcher system that does this with cloud computing. Gives example of roll cage that look…

With the exception of the antennas designed with genetic algorithms[0], the "alien" aesthetic in all of these examples looks like the output of topological optimization tools. For example: https://www.youtube.com/watch?v=igRFFMSfwSQ They emphasize that Dreamcatcher uses a "top-down" style of design, so maybe they are using deep learning for NLP to parse requirements and then feeding those requirements into normal top…

I would amazed if NLP that good existed.

Instead, I suspect top-down means something like "the part must span this bounding box, weigh no more than X grams, and survive the following forces..."

Post reply on HN