I am trying to find a tutorial on training Restricted Boltzmann machines on some dataset (e.g. MNIST), using either PyTorch or Tensorflow. The few I found are outdated.
Can you recommend any?
Asked
Active
Viewed 2,105 times
1 Answers
2
Try to look for implementations of deep belief networks.
- https://github.com/albertbup/deep-belief-network
- https://github.com/JosephGatto/Deep-Belief-Networks-Tensorflow
- https://medium.com/analytics-army/deep-belief-networks-an-introduction-1d52bb867a25
- https://skymind.ai/wiki/restricted-boltzmann-machine
- https://www.csrc.ac.cn/upload/file/20170703/1499052743888438.pdf
Piotr Rarus
- 824
- 5
- 15
-
Deep belief networks are more complicated (they are stacked RBMs). I was hoping I could find a simpler example of training an RBM. But thanks anyway, I'll take a look – a06e Nov 25 '19 at 14:46
-
You should be able to get your RBM from there. – Piotr Rarus Nov 25 '19 at 14:55
-
Unfortunately most of those links don't work with Tensorflow 2 (which I installed). It's hard for a beginner to find the required changes, but I'll try. – a06e Nov 25 '19 at 15:06