A restricted Boltzmann machine (RBM) is a stochastic neural network.
A restricted Boltzmann maschine (RBM) is a stochastic neural network. RBMs can be stacked to deep networks.
Questions tagged [rbm]
30 questions
8
votes
1 answer
Why a restricted Boltzman machine (RBM) tends to learn very similar weights?
These are 4 different weight matrices that I got after training a restricted Boltzman machine (RBM) with ~4k visible units and only 96 hidden units/weight vectors. As you can see, weights are extremely similar - even black pixels on the face are…
ffriend
- 2,801
- 16
- 18
4
votes
2 answers
How do I train an RBM on color images?
I am having a hard time understanding the strategy for inputting the color. Most tutorials on RBMs only train grayscale images.
If the image is grayscale, the input units can be binary, and I can normalize the gray scale value to [0,1], and then…
smörkex
- 141
- 3
2
votes
1 answer
Pre-train using sigmoid and train using ReLU?
Using RBMs to pre-train a deep net as in this example RBM, the activation function is sigmoid and makes the math much easier.
What are the implications after the initial weights are learned using sigmoid activation functions to switch to ReLU for…
Radu Ionescu
- 121
- 1
1
vote
1 answer
How hidden units are conditionally independent in restricted Boltzmann machines
Why explaining away concept is not applicable in restricted Boltzmann machines? Their hidden units form a V structure from which probabilistic influence can flow given the observed visible variable. Why is this a problem in deep belief nets?
GJoshi
- 11
- 1