An RBM with real-valued visible units (you don’t have to understand this slide!)

• In a mean-field logistic unit, the total input provides a linear energy- gradient and the negative entropy provides a containment function with fixed curvature. So it is impossible for the value 0.7 to have much lower free energy than both 0.8 and 0.6. This is no good for modeling real- valued data. • Using Gaussian visible units we can get much sharper predictions and alternating Gibbs sampling is still easy, though learning is slower.

energy

- entropy

0          output->         1