New answers tagged activation-function
2
votes
Why softmax training is more stable
The short answer is: Yes, it is easier to train a model using SoftMax for multiclass classification compared to sigmoid, and SoftMax generally yields better results (lower loss and higher accuracy).
...
- 121
0
votes
What does the descision boundary of a relu look like?
Adding on Ben's answer above, for anyone like me struggling with geometric terminology, a polytopal region is essentially a space bounded by multiple flat surfaces.
For easy visualization, in 2D space,...
5
votes
Accepted
Which activation function for multi-class classification gives true probability (softmax vs sigmoid)
They don't represent true probability because you'd still have to calibrate your model.
Let's imagine you're trying to classify cats and dogs in a given set of images (binary classification problem, ...
Top 50 recent answers are included