It may be not directly comparable in terms of parameters but in terms of energy usage it is. If they saved energy (in part) by designing a sparse model, isn't it a valid saving regardless?
It may be not directly comparable in terms of parameters but in terms of energy usage it is. If they saved energy (in part) by designing a sparse model, isn't it a valid saving regardless?
Writing at the intersection of AI, philosophy, and the cognitive sciences | alber.romgar@gmail.com | Get my articles for free: https://mindsoftomorrow.ck.page