sanitation@lemmy.today to Programmer Humor@programming.dev · 4 days agoNew compression techniquelemmy.todayimagemessage-square134linkfedilinkarrow-up11.18Karrow-down10file-text
arrow-up11.18Karrow-down1imageNew compression techniquelemmy.todaysanitation@lemmy.today to Programmer Humor@programming.dev · 4 days agomessage-square134linkfedilinkfile-text
minus-squarespankysalmon@fedinsfw.applinkfedilinkEnglisharrow-up8·3 days agolol no you cannot make it lossless.
minus-squareAItoothbrush@lemmy.ziplinkfedilinkEnglisharrow-up1·3 days agoYeah you can? A neural network that only relies on wheights and doesnt use random numbers will always give the same output for the same input.
minus-squarespankysalmon@fedinsfw.applinkfedilinkEnglisharrow-up2·3 days agoSo does lossy compression… same output for input of an algorithm is deterministic, not lossless…
minus-squarelad@programming.devlinkfedilinkEnglisharrow-up1·3 days agoI think, they don’t mean lossless compression with LLM, but with a neural network in general. I think it might be possible, but I’m not sure
lol no you cannot make it lossless.
Yeah you can? A neural network that only relies on wheights and doesnt use random numbers will always give the same output for the same input.
So does lossy compression… same output for input of an algorithm is deterministic, not lossless…
I think, they don’t mean lossless compression with LLM, but with a neural network in general. I think it might be possible, but I’m not sure