A really excellent BBC documentary looking at the discovery of chaos and the impact on our understanding of patterns, complex systems, physics, biology, and AI. As well as looking at Turing’s ideas on morphogenesis, or Belousov’s chemical reactions, it also touches on VIDEO FEEDBACK as a model for exploring chaos. Whilst they don’t go into loads of detail, it’s nice to see it being recognised as a research method.
it would be interesting to see how video feedback techniques could be used today in the more digital realms, i think that while some folks were excited about the basic concept of a hybrid electron/photon analog computing device, the implementations were costly, inacessabile, and difficult to calibrate. if you think about it tho the current implentation of neural nets on gpus is working in a very similar way to feedback systems ( parallel convolutional operations on matrices), but with the interesting contrast of also having feed forward loops involved as well.
ahh yes this is rad - Jim Al-Khalili is a good host (even less relevant but i enjoyed his series on Science and Islam also )
iremember watching this when it came out and crying in the part about alan turing lol so sad
i rewatched it quite recently too - the only part that hasnt aged well (imo) is the end on machine learning and AI - kind of awkward watching this now haha
I must admit I understand next to nothing about neural nets etc, but certainly I like the idea of using optical feedback systems as a bridge between digital processes. What are ‘parallel convolution matrices’? Is that how the picture gets interpreted by the camera (similar perhaps to how each step in Conways Game of Life is based on the last?)
i like to think about neural networks working in terms of signal flows. which i don’t think is remarkably standard but its like the easiest metaphors for me. the interesting thing about neural nets in terms of signal processing is that usually in signals we work with 1 dimensional systems in terms of a stream of voltage or bits, even video and image is dealt with by multiplexing. this is good enough for a lot of purposes, lots of things you would like to do in terms of processing signals can be easily done with this one at a time approach. however if you are interested in doing things with larger scale patterns in signals then it gets a little cumbersome because these patterns aren’t happening 1 bit or 1 slice of voltage at a time, they happen over a range of bits or slices of voltages so you’d then need to have some kind of a buffer around for storing chunks of data and then run convolutions on the buffer to try and extract information on a single bit’s relation with its neighborhood. a convolution is simply a weighted average of a neighborhood in some kind of stream of data. you can think of it as being like an audio filter, an image filter, or like a derivative.
it gets much easier to work with convolutions if you have a situation where you have access to every bit of data at the same time, this is basically how neural nets work, they are parallel in terms of every bit of information is processed at the same time (and massively parallel in terms of theres usually multiple levels of neural nets working in feedback and feedforward loops with one another. think about running multiple shader passes on an image for processing before it gets drawn to the screen like in a standard sharpen algorithm).
if i want to find out information about what kind of shapes are in an image its really hard to do that with individual pixels one at a time but becomes easier when dealing with clusters of pixels. this can be abstracted to any kind of data tho, emergent structures in data are difficult to deal with in the one bit at a time approach but get easier once you start clumping things together and taking advantage of emergent processes to identify emergent behaviors.
this ties in with how video feedback works in that the act of pointing a camera at a screen is a parallel computation. (well strictly speaking not 100 percent of the time but since like a good chunk of the processing is happening at the speed of light and/or the speed of electricty it’s usually close enuf for human perception). it gets massively parallel because the signal is constantly being fed back upon itself. the convolutions are happening because that is in a nutshell how video feedback works. the feedforward in this situation tho is different in terms of the human who is operating the signal chain is doing the feedforward by steering the camera, changing the signal processing, fuckin around with iris/video fx, etc etc as opposed to the kind of bland stock algorithmic feedforward goals hardcoded into neural nets.
