Here’s an unusual concept: a computer-guided mechanical neural network (video, embedded below.) Why would one want a mechanical neural network? It’s essentially a tool to explore what it would take to make physical materials work in nonstandard ways. The main part is a lattice of interlinked mechanical components. When one applies a certain force in a certain direction on one end, it causes the lattice to deform in a non-intuitive way on the other end.
To make this happen, individual mechanical elements in the lattice need to have their compliance carefully tuned under the guidance of a computer system. The mechanisms shown can be adjusted on demand while force is applied and cameras monitor the results.
This feedback loop allows researchers to use the same techniques for training neural networks that are used in machine learning applications. Ultimately, a lattice can be configured in such a way that when side A is pressed like this, side B moves like that.
We’ve seen compliant structures that move in unexpected ways before, and they are always fascinating. One example is this 3D-printed door latch that translates a twisting motion into a linear one. Research into physical neural networks seems like it might open the door to more complex systems, or provide insights into metamaterial design.
You can watch the video below just under the page break, or if you prefer, skip the intro and jump straight into How It Works at [2:32].
sometimes i feel like hack a day is just reading my youtube history.
I guess they get recommended the same videos we all do too
And YT learns from every embedded video who is visiting HaD (don’t they?).
Even as so far that i see a link to a hackaday-isch video, i don’t click it as a post here will soon arrive so I don’t have to watch it to know if its worth my time. Very handy…
This reminds me of David Brin’s novel The Practice Effect, where things get better and more efficient with use.
Unfortunately that was replaced by The Monetisation Effect.
Now to replace those solenoids with layers of mems devices or even better, individual mems devices in a conductive paint.
Or far better, transistors
Useless for machine learning, but I have a strong suspicion that this opens up astounding opportunities for physical metamaterials.
R: Holy hype, Batman! The extrapolations in his examples exceed every expectation!
B: Not now Robin, I’m watching clickbait on Youtube.
“might open the door” – I see what you did there :-)