Boltzmann Machines

Why use a generative model rather than the more well known discriminative deep neural networks (DNN)?

• Discriminitave methods have several limitations: They are mainly supervised learning methods, thus requiring labeled data. And there are tasks they cannot accomplish, like drawing new examples from an unknown probability distribution.
• A generative model can learn to represent and sample from a probability distribution. The core idea is to learn a parametric model of the probability distribution from which the training data was drawn. As an example
  1. A model for images could learn to draw new examples of cats and dogs, given a training dataset of images of cats and dogs.
  2. Generate a sample of an ordered or disordered Ising model phase, having been given samples of such phases.
  3. Model the trial function for Monte Carlo calculations

• «
• 1
• ...
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• ...
• 60
• »