alott's Profile

1000
Points

Questions
0

Answers
1

  • Asked on May 16, 2016 in Machine Learning.

    One of the major advantages to considering quantum computing – specifically quantum annealing for  machine learning is  that the solutions can be viewed as samples  from a Boltzmann distribution. This is a very difficult computational process, that is typically approximated by a Markov Chain Monte Carlo method.  If one can effectively sample from a Boltzmann distribution, then building probabilistic models based on the joint-probability distribution is in reach. This opens the doors to generative learning algorithms that can provide a much richer statistical framework for guiding experiments, performing model selection, model averaging etc.  In short, with a quantum computer, one can integrate principles of probabilistic uncertainty into machine learning algorithms, as opposed to purely deterministic models.

    • 4731 views
    • 3 answers
    • 0 votes