RBM¶

class qucumber.rbm.BinaryRBM(num_visible, num_hidden, zero_weights=False, gpu=True)[source]¶

Bases: torch.nn.modules.module.Module

effective_energy(v)[source]¶

The effective energies of the given visible states.

$\mathcal{E}(\bm{v}) &= -\sum_{j}b_j v_j - \sum_{i}\log \left\lbrack 1 + \exp\left(c_{i} + \sum_{j} W_{ij} v_j\right) \right\rbrack$

Parameters:	v (torch.Tensor) – The visible states.
Returns:	The effective energies of the given visible states.
Return type:	torch.Tensor

effective_energy_gradient(v)[source]¶

The gradients of the effective energies for the given visible states.

Parameters:	v (torch.Tensor) – The visible states.
Returns:	1d vector containing the gradients for all parameters (computed on the given visible states v).
Return type:	torch.Tensor

gibbs_steps(k, initial_state, overwrite=False)[source]¶

Performs k steps of Block Gibbs sampling. One step consists of sampling the hidden state $\bm{h}$ from the conditional distribution $p(\bm{h}\:|\:\bm{v})$ , and sampling the visible state $\bm{v}$ from the conditional distribution $p(\bm{v}\:|\:\bm{h})$ .

Parameters:	k (int) – Number of Block Gibbs steps. initial_state (torch.Tensor) – The initial state of the Markov Chain. If given, num_samples will be ignored. overwrite (bool) – Whether to overwrite the initial_state tensor, if it is provided.

initialize_parameters(zero_weights=False)[source]¶: Randomize the parameters of the RBM

partition(space)[source]¶

Compute the partition function of the RBM.

Parameters:	space (torch.Tensor) – A rank 2 tensor of the visible space.
Returns:	The value of the partition function evaluated at the current state of the RBM.
Return type:	torch.Tensor

prob_h_given_v(v, out=None)[source]¶

Given a visible unit configuration, compute the probability vector of the hidden units being on.

Parameters:	h (torch.Tensor) – The hidden unit. out (torch.Tensor) – The output tensor to write to.
Returns:	The probability of hidden units being active given the visible state.
Return type:	torch.Tensor

prob_v_given_h(h, out=None)[source]¶

Given a hidden unit configuration, compute the probability vector of the visible units being on.

Parameters:	h (torch.Tensor) – The hidden unit out (torch.Tensor) – The output tensor to write to.
Returns:	The probability of visible units being active given the hidden state.
Return type:	torch.Tensor

sample_h_given_v(v, out=None)[source]¶

Sample/generate a hidden state given a visible state.

Parameters:	h (torch.Tensor) – The visible state. out (torch.Tensor) – The output tensor to write to.
Returns:	Tuple containing prob_h_given_v(v) and the sampled hidden state.
Return type:	tuple(torch.Tensor, torch.Tensor)

sample_v_given_h(h, out=None)[source]¶

Sample/generate a visible state given a hidden state.

Parameters:	h (torch.Tensor) – The hidden state. out (torch.Tensor) – The output tensor to write to.
Returns:	Tuple containing prob_v_given_h(h) and the sampled visible state.
Return type:	tuple(torch.Tensor, torch.Tensor)