gedaliyah@lemmy.world to Lemmy Shitpost@lemmy.worldEnglish · 7 days agoAutomationlemmy.worldimagemessage-square162fedilinkarrow-up11.76K
arrow-up11.76KimageAutomationlemmy.worldgedaliyah@lemmy.world to Lemmy Shitpost@lemmy.worldEnglish · 7 days agomessage-square162fedilink
minus-squaredondelelcaro@lemmy.worldlinkfedilinkarrow-up4·6 days agoExactly. The general approach is to use interpretable models where you can understand how the model works and what features it uses to discriminate, but that doesn’t work for all ML approaches (and even when it does our understanding is incomplete.)
Exactly.
The general approach is to use interpretable models where you can understand how the model works and what features it uses to discriminate, but that doesn’t work for all ML approaches (and even when it does our understanding is incomplete.)