quantax.model.RBM_Conv

quantax.model.RBM_Conv(channels: int, use_bias: bool = True, dtype: ~numpy.dtype = <class 'jax.numpy.float32'>)

The restricted Boltzmann machine with one convolutional layer \(\psi(s) = \prod \cosh(\mathrm{Conv}(s))\).

Parameters:

• features – The number of channels in the convolutional network.

• use_bias – Whether to add on a bias in the convolution.

• dtype – The data type of the parameters.