Epzillon@lemmy.world to Lemmy Shitpost@lemmy.world · 14 天前no one can understand AIlemmy.worldimagemessage-square40fedilinkarrow-up1484arrow-down129 cross-posted to: [email protected]
arrow-up1455arrow-down1imageno one can understand AIlemmy.worldEpzillon@lemmy.world to Lemmy Shitpost@lemmy.world · 14 天前message-square40fedilink cross-posted to: [email protected]
minus-squarered_tomato@lemmy.worldlinkfedilinkarrow-up50·14 天前It’s just y = k*x + m a few trillion times.
minus-squarecathfish@lemmy.worldlinkfedilinkarrow-up8·14 天前Yes it’s not even for loop and if. Just multiplication and addition.
minus-squareMirodir@discuss.tchncs.delinkfedilinkarrow-up2·13 天前You’re forgetting the activation function to break linearity, otherwise you can only model linear trends. Many activation functions have “if” hidden in them (e.g. ReLU with the “max”).
It’s just
y = k*x + ma few trillion times.Yes it’s not even for loop and if. Just multiplication and addition.
You’re forgetting the activation function to break linearity, otherwise you can only model linear trends. Many activation functions have “if” hidden in them (e.g. ReLU with the “max”).