pancratm

I have read the article: Attentive State-Space Modeling of Disease Progression and I think the algorithm is very valuable. But I am still not sure how the author applies this...

I tried to apply this model to a regression problem, but the y_pred obtained in the model.predicT_y (X) step is always a value greater than 0 and less than 1....

Whether the centroids have been updated?

1

When the code is run to cluster in train_ClusterNET() function and compute Q/P in forward(), the similarity computed based on self.centroids which are always stay the same. Will the centroids...

It seems impossible to do so according to the 'ax' obtained.