Open sankar-mukherjee opened 5 years ago
It's implemented! iirc it should be runnable with cortex mine --help
, but I've been working mostly on the next release of cortex so I don't know for sure.
thanks i will try to run it. I just have another question. could you measure mutual information between different dimension time varying signals with your implementation? for example i want to compute MI between 300 dim and 1 dim signal.
So the implementation as-is is set up for image data and gaussian noise. So while there are no constraints about the dimensionality of either variables, the networks used are suitable for image and (unstructured) noise data. However, the core loss functions / routines should remain the same.
Hello Dr. Devon Hjelm, I was searching for the implementation of Mutual Information Neural Estimation and i came accross your code. But i am not sure if its implemented!! Could you please help me on how to use it ?
Regards, Sankar Mukherjee