More about RBMs

1. Useful when we model continuous data (i.e., we wish \( \mathbf{x} \) to be continuous)
2. Requires a smaller learning rate, since there's no upper bound to the value a component might take in the reconstruction

Other types of units include:

1. Softmax and multinomial units
2. Gaussian visible and hidden units
3. Binomial units
4. Rectified linear units

To read more, see Lectures on Boltzmann machines in Physics.

• «
• 1
• ...
• 53
• 54
• 55
• 56
• 57
• 58
• 59
• 60
• 61
• 62
• 63
• 64
• 65
• 66
• 67
• 68
• 69
• 70
• ...
• 80
• »