Does it work better than original nerual network in binary classification

alvinwan / neural-backed-decision-trees

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

https://nbdt.aaalv.in

MIT License

607 stars 130 forks source link

Does it work better than original nerual network in binary classification #23

Open study1157 opened 2 years ago

study1157 commented 2 years ago

I mean apply NBDT with soft loss.., you know the inner node weight can't be update with the soft loss in binary classfication due to the special inner probability computing method.