222bakteri

Hi, Thank you for your post,it helps me a lot. I tried to train Guassianbinary RBM with my data,which consists of real number ranging from -100 to 100. But the...

In original paper the output map size are 32,16,8 respectively;However in your code it seems that they are 64,32,16. Did I miss anything?

About training process

2

It seems that there is no training process in your code,only including forward prop and prediction.Did I miss something?

Trianing speed is super slow with your L-BFGS

2

Hi, Thank you for your post, it helps a lot. However when I tried to use it I found that it ios very slow even with GPU. With SGU and...