Method reconstruct

numpy_ml/neural_nets/layers/layers.py:587–625

Reconstruct an input `X` by running the trained Gibbs sampler for `n_steps`-worth of CD-`k`. Parameters ---------- X : :py:class:`ndarray ` of shape `(n_ex, n_in)` Layer input, representing the `n_in`-dimensional features for a

(self, X, n_steps=10, return_prob=False)

            self.gradients["W"] = positive_grad - negative_grad

    def reconstruct(self, X, n_steps=10, return_prob=False):
        """
        Reconstruct an input `X` by running the trained Gibbs sampler for
        `n_steps`-worth of CD-`k`.

        Parameters
        ----------
        X : :py:class:`ndarray <numpy.ndarray>` of shape `(n_ex, n_in)`
            Layer input, representing the `n_in`-dimensional features for a
            minibatch of `n_ex` examples. Each feature in `X` should ideally be
            binary-valued, although it is possible to also train on real-valued
            features ranging between (0, 1) (e.g., grayscale images). If `X` has
            missing values, it may be sufficient to mark them with random
            entries and allow the reconstruction to impute them.
        n_steps : int
            The number of Gibbs sampling steps to perform when generating the
            reconstruction. Default is 10.
        return_prob : bool
            Whether to return the real-valued feature probabilities for the
            reconstruction or the binary samples. Default is False.

        Returns
        -------
        V : :py:class:`ndarray <numpy.ndarray>` of shape `(n_ex, in_ch)`
            The reconstruction (or feature probabilities if `return_prob` is
            true) of the visual input `X` after running the Gibbs sampler for
            `n_steps`.
        """
        self.forward(X, K=n_steps)
        p_V_prime = self.derived_variables["p_V_prime"]

        # ignore the gradients produced during this reconstruction
        self.flush_gradients()

        # sample V_prime reconstruction if return_prob is False
        V = p_V_prime
        if not return_prob:
            V = (np.random.rand(*p_V_prime.shape) <= p_V_prime).astype(float)
        return V


#######################################################################