诶,这个巧妙,他这个巧妙(lottery ticket hypothesis)
版主: huangchong
#2 Re: 诶,这个巧妙,他这个巧妙(lottery ticket hypothesis)
"lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.
有点像deepseek的专家模型
有点像deepseek的专家模型
¡qooq ƃᴉq ɐ ǝɹɐ no⅄
#3 Re: 诶,这个巧妙,他这个巧妙(lottery ticket hypothesis)
good pointɓuoɥɔɓuɐnɥ 写了: 2025年 3月 30日 13:03 "lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.
有点像deepseek的专家模型