Hacker News Reader

Comment by ainch | Hacker News Reader

This method is cool and the post explains it well. It would, however, be good to get more detail on the energy efficiency they flag as their motivation: is this model actually more energy efficient than the comparators they highlight?

View on HN

It seems like total parameter count is more or less on par with conventional approaches so any gains won't be from there.

We can implement coupled oscillators in hardware but are the couplings and frequencies programmable? If they're being streamed in I guess you'd still have a memory bandwidth bottleneck and associated energy usage. If not then the fair comparison is to a conventional model hardcoded in an ASIC which AFAIU is actually quite energy efficient.

Do the parameters in these harmonic systems compress better? Instead of needing to hold individual parameters for each oscillator, could groupings of oscillators be instead be described with its output over a given time and then just reverse that output to get the original parameters (I’m thinking the output is like an FFT of the oscillators which is a single value, then do an inverse FFT to get the original oscillator parameters etc)

You mean describing the core of the system via its normal mode or similar or even performing normal mode analysis to recover it from a waveform? I have no idea how that performs as a lossy compression method versus other options such as quantization but regardless I'm fairly certain it would be computationally infeasible given the application.

Yeah, I was talking about recovery. I’ve always wondered if systems could be compressed via trying to curve fit generators like these oscillators.

… I still hold hope metaheuristics could at least do a good job of approximating. One day I’ll have time to play and go down the rabbit hole

Reply on news.ycombinator.com