ds.bm.samples: Generate samples from a Boltzmann machine model
In stefan-m-lenz/dsBoltzmannMachinesClient: Client for dsBoltzmannMachines

A Gibbs sampler is run in the Boltzmann machine model to sample from the learnt distribution. This can also be used for sampling from a conditional distribution (see arguments conditionIndex and conditionValue below.)

ds.bm.samples(
  datasources,
  bm,
  nsamples,
  burnin = NULL,
  conditionIndex = NULL,
  conditionValue = NULL,
  samplelast = NULL
)

`datasources`	A list of Opal object(s) as a handle to the server-side session
`bm`	The name of the model to sample from on the server-side
`nsamples`	The number of samples to generate
`burnin`	The number of Gibbs sampling steps, defaults to 50.
`conditionIndex`	A vector containing indices of variables that are to be conditioned on
`conditionValue`	A vector containing the values for the variables that are to be conditioned on. (must be of same length as `conditionIndex`)
`samplelast`	boolean to indicate whether to sample in the last step (`TRUE`, default) or whether to use the deterministic activation potential.