[HN Gopher] A Mechanical Neural Network Learns to Respond to Its... ___________________________________________________________________ A Mechanical Neural Network Learns to Respond to Its Environment Author : _Microft Score : 24 points Date : 2022-10-20 17:56 UTC (3 days ago) (HTM) web link (www.hackster.io) (TXT) w3m dump (www.hackster.io) | akihitosan wrote: | I think to call a big machine a material is very wrong. | mach1ne wrote: | >Learns to Respond to Its Environment | | So we're back at this kind of antropomorphization. | juunpp wrote: | *Anthropos, and as if learning was unique to humans? What is | learning anyway if not the adaptation of the brain to its | inputs? | andrewflnr wrote: | Given the title "Mechanical Neural Network", the presence of a | conventional digital computer is really disappointing. I went in | to this article hoping for steampunk AI. | abecedarius wrote: | Here's an idea: ReLU basically = a seesaw + ropes that attach | at a movable distance from the fulcrum. Adjusting a 'weight' = | sliding the attachment. Nonlinearity = rope can pull but not | push. | | I'm afraid getting the details to work in practice would | probably be horrible. | | Not steampunk but sort of biopunk: years ago someone programmed | a DNA strand displacement mechanism to implement a particular | fixed neural network, as a proof of concept. | iNic wrote: | I don't understand the advantage of this over just having a | digital NN and then pushing the output to some electric motor? | mjburgess wrote: | It depends on how much koolaid you've drunk. | | A NN implemented on a digital computer is a fixed way of | varying the electrical field of the CPU (etc.) given (eg.,) an | SSD state which produces a fixed way of varying (eg.,) a motor. | | This is very (very) far away from adaptive motion at the | "tissue" level. | | The semi-mystical notion that a NN is a kind of "programming of | reality" is false: just as a NN running on a CPU cannot perform | nuclear fusion, it likewise, cannot produce material | adaptation. | | It is an open question whether any non-organic material is | adaptive, and I'd bet against it. | rongopo wrote: | Indeed there is not such advantage. | bufferoverflow wrote: | I think you're missing the point. I think it's to demonstrate | that fully mechanical systems can learn and react like a real | brain plus muscles and sensors. | | The possible implication is, if consciousness can arise in a | digital neural net, it can also arise in a mechanical system, | you just need enough of levers and gears connected in a certain | way. | djokkataja wrote: | > I think it's to demonstrate that fully mechanical systems | can learn and react like a real brain plus muscles and | sensors. | | That wasn't the point of the research as expressed in the | article (note that the final image has a label for "Control | electronics" underneath the mechanical system): | | > Thus, this work lays the foundation for artificial- | intelligent (AI) materials that can learn behaviors and | properties. | | With applications such as: | | > use in aircraft wings to morph the shape in response to | wind patterns to boost efficiency, adding reactive rigidity | to buildings to better withstand earthquakes and other | disasters, shockwave-deflecting reactive armor, or even the | creation of surfaces able to perform acoustic imaging. | rongopo wrote: | What is the point of the video?? ___________________________________________________________________ (page generated 2022-10-23 23:00 UTC)