diff --git a/GPy/core/GP.py b/GPy/core/GP.py
new file mode 100644
index 00000000..856c8a5c
--- /dev/null
+++ b/GPy/core/GP.py
@@ -0,0 +1,146 @@
+# Copyright (c) 2012, GPy authors (see AUTHORS.txt).
+# Licensed under the BSD 3-clause license (see LICENSE.txt)
+
+
+import numpy as np
+from scipy import linalg
+import pylab as pb
+from .. import kern
+from ..util.linalg import pdinv, mdot, tdot
+#from ..util.plot import gpplot,  Tango
+from ..likelihoods import EP
+from gp_base import GPBase
+
+class GP(GPBase):
+    """
+    Gaussian Process model for regression and EP
+
+    :param X: input observations
+    :param kernel: a GPy kernel, defaults to rbf+white
+    :parm likelihood: a GPy likelihood
+    :param normalize_X:  whether to normalize the input data before computing (predictions will be in original scales)
+    :type normalize_X: False|True
+    :rtype: model object
+    :param epsilon_ep: convergence criterion for the Expectation Propagation algorithm, defaults to 0.1
+    :param powerep: power-EP parameters [$\eta$,$\delta$], defaults to [1.,1.]
+    :type powerep: list
+
+    .. Note:: Multiple independent outputs are allowed using columns of Y
+
+    """
+    def __init__(self, X, likelihood, kernel, normalize_X=False):
+        super(GP, self).__init__(X, likelihood, kernel, normalize_X=normalize_X)
+        self._set_params(self._get_params())
+
+    def _set_params(self, p):
+        self.kern._set_params_transformed(p[:self.kern.Nparam_transformed()])
+        self.likelihood._set_params(p[self.kern.Nparam_transformed():])
+
+        self.K = self.kern.K(self.X)
+        self.K += self.likelihood.covariance_matrix
+
+        self.Ki, self.L, self.Li, self.K_logdet = pdinv(self.K)
+
+        # the gradient of the likelihood wrt the covariance matrix
+        if self.likelihood.YYT is None:
+            #alpha = np.dot(self.Ki, self.likelihood.Y)
+            alpha,_ = linalg.lapack.flapack.dpotrs(self.L, self.likelihood.Y,lower=1)
+
+            self.dL_dK = 0.5 * (tdot(alpha) - self.D * self.Ki)
+        else:
+            #tmp = mdot(self.Ki, self.likelihood.YYT, self.Ki)
+            tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(self.likelihood.YYT), lower=1)
+            tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(tmp.T), lower=1)
+            self.dL_dK = 0.5 * (tmp - self.D * self.Ki)
+
+    def _get_param_names(self):
+        return self.kern._get_param_names_transformed() + self.likelihood._get_param_names()
+
+    def update_likelihood_approximation(self):
+        """
+        Approximates a non-gaussian likelihood using Expectation Propagation
+
+        For a Gaussian likelihood, no iteration is required:
+        this function does nothing
+        """
+        self.likelihood.fit_full(self.kern.K(self.X))
+        self._set_params(self._get_params())  # update the GP
+
+    def _model_fit_term(self):
+        """
+        Computes the model fit using YYT if it's available
+        """
+        if self.likelihood.YYT is None:
+            tmp, _ = linalg.lapack.flapack.dtrtrs(self.L, np.asfortranarray(self.likelihood.Y), lower=1)
+            return -0.5 * np.sum(np.square(tmp))
+            #return -0.5 * np.sum(np.square(np.dot(self.Li, self.likelihood.Y)))
+        else:
+            return -0.5 * np.sum(np.multiply(self.Ki, self.likelihood.YYT))
+
+    def log_likelihood(self):
+        """
+        The log marginal likelihood of the GP.
+
+        For an EP model,  can be written as the log likelihood of a regression
+        model for a new variable Y* = v_tilde/tau_tilde, with a covariance
+        matrix K* = K + diag(1./tau_tilde) plus a normalization term.
+        """
+        return -0.5 * self.D * self.K_logdet + self._model_fit_term() + self.likelihood.Z
+
+
+    def _log_likelihood_gradients(self):
+        """
+        The gradient of all parameters.
+
+        Note, we use the chain rule: dL_dtheta = dL_dK * d_K_dtheta
+        """
+        return np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK))))
+
+    def _raw_predict(self, _Xnew, which_parts='all', full_cov=False,stop=False):
+        """
+        Internal helper function for making predictions, does not account
+        for normalization or likelihood
+        """
+        Kx = self.kern.K(_Xnew,self.X,which_parts=which_parts).T
+        #KiKx = np.dot(self.Ki, Kx)
+        KiKx, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(Kx), lower=1)
+        mu = np.dot(KiKx.T, self.likelihood.Y)
+        if full_cov:
+            Kxx = self.kern.K(_Xnew, which_parts=which_parts)
+            var = Kxx - np.dot(KiKx.T, Kx)
+        else:
+            Kxx = self.kern.Kdiag(_Xnew, which_parts=which_parts)
+            var = Kxx - np.sum(np.multiply(KiKx, Kx), 0)
+            var = var[:, None]
+        if stop:
+            debug_this
+        return mu, var
+
+    def predict(self, Xnew, which_parts='all', full_cov=False):
+        """
+        Predict the function(s) at the new point(s) Xnew.
+        Arguments
+        ---------
+        :param Xnew: The points at which to make a prediction
+        :type Xnew: np.ndarray, Nnew x self.Q
+        :param which_parts:  specifies which outputs kernel(s) to use in prediction
+        :type which_parts: ('all', list of bools)
+        :param full_cov: whether to return the folll covariance matrix, or just the diagonal
+        :type full_cov: bool
+        :rtype: posterior mean,  a Numpy array, Nnew x self.D
+        :rtype: posterior variance, a Numpy array, Nnew x 1 if full_cov=False, Nnew x Nnew otherwise
+        :rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays,  Nnew x self.D
+
+
+           If full_cov and self.D > 1, the return shape of var is Nnew x Nnew x self.D. If self.D == 1, the return shape is Nnew x Nnew.
+           This is to allow for different normalizations of the output dimensions.
+
+        """
+        # normalize X values
+        Xnew = (Xnew.copy() - self._Xmean) / self._Xstd
+        mu, var = self._raw_predict(Xnew, full_cov=full_cov, which_parts=which_parts)
+
+        # now push through likelihood
+        mean, var, _025pm, _975pm = self.likelihood.predictive_values(mu, var, full_cov)
+
+        return mean, var, _025pm, _975pm
diff --git a/GPy/core/__init__.py b/GPy/core/__init__.py
index bb97b04e..e49541b0 100644
--- a/GPy/core/__init__.py
+++ b/GPy/core/__init__.py
@@ -1,7 +1,8 @@
 # Copyright (c) 2012, GPy authors (see AUTHORS.txt).
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 
-
+from GP import GP
+from sparse_GP import sparse_GP
 from model import *
 from parameterised import *
 import priors
diff --git a/GPy/core/gp_base.py b/GPy/core/gp_base.py
new file mode 100644
index 00000000..8df1a5c1
--- /dev/null
+++ b/GPy/core/gp_base.py
@@ -0,0 +1,129 @@
+import numpy as np
+import model
+from .. import kern
+from ..util.plot import gpplot, Tango, x_frame1D, x_frame2D
+import pylab as pb
+
+class GPBase(model):
+    """
+    Gaussian Process model for holding shared behaviour between
+    sprase_GP and GP models
+    """
+
+    def __init__(self, X, likelihood, kernel, normalize_X=False):
+        self.X = X
+        assert len(self.X.shape) == 2
+        self.N, self.Q = self.X.shape
+        assert isinstance(kernel, kern.kern)
+        self.kern = kernel
+        self.likelihood = likelihood
+        assert self.X.shape[0] == self.likelihood.data.shape[0]
+        self.N, self.D = self.likelihood.data.shape
+
+        if normalize_X:
+            self._Xmean = X.mean(0)[None, :]
+            self._Xstd = X.std(0)[None, :]
+            self.X = (X.copy() - self._Xmean) / self._Xstd
+
+        super(GPBase, self).__init__()
+
+        # All leaf nodes should call self._set_params(self._get_params()) at
+        # the end
+
+    def _get_params(self):
+        return np.hstack((self.kern._get_params_transformed(), self.likelihood._get_params()))
+
+    def plot_f(self, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, full_cov=False):
+        """
+        Plot the GP's view of the world, where the data is normalized and the
+        likelihood is Gaussian.
+
+        :param samples: the number of a posteriori samples to plot
+        :param which_data: which if the training data to plot (default all)
+        :type which_data: 'all' or a slice object to slice self.X, self.Y
+        :param plot_limits: The limits of the plot. If 1D [xmin,xmax], if 2D [[xmin,ymin],[xmax,ymax]]. Defaluts to data limits
+        :param which_parts: which of the kernel functions to plot (additively)
+        :type which_parts: 'all', or list of bools
+        :param resolution: the number of intervals to sample the GP on. Defaults to 200 in 1D and 50 (a 50x50 grid) in 2D
+
+        Plot the posterior of the GP.
+          - In one dimension, the function is plotted with a shaded region identifying two standard deviations.
+          - In two dimsensions, a contour-plot shows the mean predicted function
+          - In higher dimensions, we've no implemented this yet !TODO!
+
+        Can plot only part of the data and part of the posterior functions
+        using which_data and which_functions
+        """
+        if which_data == 'all':
+            which_data = slice(None)
+
+        if self.X.shape[1] == 1:
+            Xnew, xmin, xmax = x_frame1D(self.X, plot_limits=plot_limits)
+            if samples == 0:
+                m, v = self._raw_predict(Xnew, which_parts=which_parts)
+                gpplot(Xnew, m, m - 2 * np.sqrt(v), m + 2 * np.sqrt(v))
+                pb.plot(self.X[which_data], self.likelihood.Y[which_data], 'kx', mew=1.5)
+            else:
+                m, v = self._raw_predict(Xnew, which_parts=which_parts, full_cov=True)
+                Ysim = np.random.multivariate_normal(m.flatten(), v, samples)
+                gpplot(Xnew, m, m - 2 * np.sqrt(np.diag(v)[:, None]), m + 2 * np.sqrt(np.diag(v))[:, None])
+                for i in range(samples):
+                    pb.plot(Xnew, Ysim[i, :], Tango.colorsHex['darkBlue'], linewidth=0.25)
+            pb.plot(self.X[which_data], self.likelihood.Y[which_data], 'kx', mew=1.5)
+            pb.xlim(xmin, xmax)
+            ymin, ymax = min(np.append(self.likelihood.Y, m - 2 * np.sqrt(np.diag(v)[:, None]))), max(np.append(self.likelihood.Y, m + 2 * np.sqrt(np.diag(v)[:, None])))
+            ymin, ymax = ymin - 0.1 * (ymax - ymin), ymax + 0.1 * (ymax - ymin)
+            pb.ylim(ymin, ymax)
+            if hasattr(self, 'Z'):
+                pb.plot(self.Z, self.Z * 0 + pb.ylim()[0], 'r|', mew=1.5, markersize=12)
+
+        elif self.X.shape[1] == 2:
+            resolution = resolution or 50
+            Xnew, xmin, xmax, xx, yy = x_frame2D(self.X, plot_limits, resolution)
+            m, v = self._raw_predict(Xnew, which_parts=which_parts)
+            m = m.reshape(resolution, resolution).T
+            pb.contour(xx, yy, m, vmin=m.min(), vmax=m.max(), cmap=pb.cm.jet)
+            pb.scatter(self.X[:, 0], self.X[:, 1], 40, self.likelihood.Y, linewidth=0, cmap=pb.cm.jet, vmin=m.min(), vmax=m.max())
+            pb.xlim(xmin[0], xmax[0])
+            pb.ylim(xmin[1], xmax[1])
+        else:
+            raise NotImplementedError, "Cannot define a frame with more than two input dimensions"
+
+    def plot(self, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, levels=20):
+        """
+        TODO: Docstrings!
+        :param levels: for 2D plotting, the number of contour levels to use
+
+        """
+        # TODO include samples
+        if which_data == 'all':
+            which_data = slice(None)
+
+        if self.X.shape[1] == 1:
+
+            Xu = self.X * self._Xstd + self._Xmean  # NOTE self.X are the normalized values now
+
+            Xnew, xmin, xmax = x_frame1D(Xu, plot_limits=plot_limits)
+            m, var, lower, upper = self.predict(Xnew, which_parts=which_parts)
+            for d in range(m.shape[1]):
+                gpplot(Xnew, m[:,d], lower[:,d], upper[:,d])
+                pb.plot(Xu[which_data], self.likelihood.data[which_data,d], 'kx', mew=1.5)
+            ymin, ymax = min(np.append(self.likelihood.data, lower)), max(np.append(self.likelihood.data, upper))
+            ymin, ymax = ymin - 0.1 * (ymax - ymin), ymax + 0.1 * (ymax - ymin)
+            pb.xlim(xmin, xmax)
+            pb.ylim(ymin, ymax)
+
+        elif self.X.shape[1] == 2:  # FIXME
+            resolution = resolution or 50
+            Xnew, xx, yy, xmin, xmax = x_frame2D(self.X, plot_limits, resolution)
+            x, y = np.linspace(xmin[0], xmax[0], resolution), np.linspace(xmin[1], xmax[1], resolution)
+            m, var, lower, upper = self.predict(Xnew, which_parts=which_parts)
+            m = m.reshape(resolution, resolution).T
+            pb.contour(x, y, m, levels, vmin=m.min(), vmax=m.max(), cmap=pb.cm.jet)
+            Yf = self.likelihood.Y.flatten()
+            pb.scatter(self.X[:, 0], self.X[:, 1], 40, Yf, cmap=pb.cm.jet, vmin=m.min(), vmax=m.max(), linewidth=0.)
+            pb.xlim(xmin[0], xmax[0])
+            pb.ylim(xmin[1], xmax[1])
+
+        else:
+            raise NotImplementedError, "Cannot define a frame with more than two input dimensions"
diff --git a/GPy/core/model.py b/GPy/core/model.py
index 5dc6b254..dea55319 100644
--- a/GPy/core/model.py
+++ b/GPy/core/model.py
@@ -22,8 +22,8 @@ class model(parameterised):
         self.priors = [None for i in range(self._get_params().size)]
         self.optimization_runs = []
         self.sampling_runs = []
-        self._set_params(self._get_params())
         self.preferred_optimizer = 'tnc'
+        #self._set_params(self._get_params()) has been taken out as it should only be called on leaf nodes
     def _get_params(self):
         raise NotImplementedError, "this needs to be implemented to use the model class"
     def _set_params(self, x):
diff --git a/GPy/models/sparse_GP.py b/GPy/core/sparse_GP.py
similarity index 91%
rename from GPy/models/sparse_GP.py
rename to GPy/core/sparse_GP.py
index fad18dc6..89632aa1 100644
--- a/GPy/models/sparse_GP.py
+++ b/GPy/core/sparse_GP.py
@@ -4,13 +4,12 @@
 import numpy as np
 import pylab as pb
 from ..util.linalg import mdot, jitchol, tdot, symmetrify, backsub_both_sides, chol_inv
-from ..util.plot import gpplot
-from .. import kern
 from GP import GP
 from scipy import linalg
 from ..likelihoods import Gaussian
+from gp_base import GPBase
 
-class sparse_GP(GP):
+class sparse_GP(GPBase):
     """
     Variational sparse GP model
 
@@ -31,6 +30,8 @@ class sparse_GP(GP):
     """
 
     def __init__(self, X, likelihood, kernel, Z, X_variance=None, normalize_X=False):
+        super(sparse_GP, self).__init__(X, likelihood, kernel, normalize_X=normalize_X)
+
         self.Z = Z
         self.M = Z.shape[0]
         self.likelihood = likelihood
@@ -42,13 +43,13 @@ class sparse_GP(GP):
             self.has_uncertain_inputs = True
             self.X_variance = X_variance
 
-        GP.__init__(self, X, likelihood, kernel=kernel, normalize_X=normalize_X)
+        if normalize_X:
+            self.Z = (self.Z.copy() - self._Xmean) / self._Xstd
 
         # normalize X uncertainty also
         if self.has_uncertain_inputs:
             self.X_variance /= np.square(self._Xstd)
 
-
     def _compute_kernel_matrices(self):
         # kernel computations, using BGPLVM notation
         self.Kmm = self.kern.K(self.Z)
@@ -139,8 +140,6 @@ class sparse_GP(GP):
             self.partial_for_likelihood += 0.5 * self.D * (self.psi0.sum() * self.likelihood.precision ** 2 - np.trace(self.A) * self.likelihood.precision)
             self.partial_for_likelihood += self.likelihood.precision * (0.5 * np.sum(self.A * self.DBi_plus_BiPBi) - np.sum(np.square(self._LBi_Lmi_psi1V)))
 
-
-
     def log_likelihood(self):
         """ Compute the (lower bound on the) log marginal likelihood """
         if self.likelihood.is_heteroscedastic:
@@ -282,3 +281,17 @@ class sparse_GP(GP):
 
         return mean, var, _025pm, _975pm
 
+    def plot(self, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, levels=20):
+        super(sparse_GP, self).plot(samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, levels=20)
+        if self.X.shape[1] == 1:
+            Xu = self.X * self._Xstd + self._Xmean  # NOTE self.X are the normalized values now
+            if self.has_uncertain_inputs:
+                pb.errorbar(Xu[which_data, 0], self.likelihood.data[which_data, 0],
+                            xerr=2 * np.sqrt(self.X_variance[which_data, 0]),
+                            ecolor='k', fmt=None, elinewidth=.5, alpha=.5)
+            Zu = self.Z * self._Xstd + self._Xmean
+            pb.plot(Zu, Zu * 0 + pb.ylim()[0], 'r|', mew=1.5, markersize=12)
+                # pb.errorbar(self.X[:,0], pb.ylim()[0]+np.zeros(self.N), xerr=2*np.sqrt(self.X_variance.flatten()))
+
+        elif self.X.shape[1] == 2:  # FIXME
+            pb.plot(self.Z[:, 0], self.Z[:, 1], 'wo')
diff --git a/GPy/models/Bayesian_GPLVM.py b/GPy/models/Bayesian_GPLVM.py
index 5f22526b..52779e8e 100644
--- a/GPy/models/Bayesian_GPLVM.py
+++ b/GPy/models/Bayesian_GPLVM.py
@@ -5,7 +5,7 @@ import numpy as np
 import pylab as pb
 import sys, pdb
 from GPLVM import GPLVM
-from sparse_GP import sparse_GP
+from ..core import sparse_GP
 from GPy.util.linalg import pdinv
 from ..likelihoods import Gaussian
 from .. import kern
@@ -65,6 +65,7 @@ class Bayesian_GPLVM(sparse_GP, GPLVM):
             self._savedABCD = []
 
         sparse_GP.__init__(self, X, likelihood, kernel, Z=Z, X_variance=X_variance, **kwargs)
+        self._set_params(self._get_params())
 
     @property
     def oldps(self):
@@ -96,7 +97,7 @@ class Bayesian_GPLVM(sparse_GP, GPLVM):
 
     def _clipped(self, x):
         return x # np.clip(x, -1e300, 1e300)
-    
+
     def _set_params(self, x, save_old=True, save_count=0):
 #         try:
             x = self._clipped(x)
diff --git a/GPy/models/FITC.py b/GPy/models/FITC.py
index 0f948d32..da2c4d84 100644
--- a/GPy/models/FITC.py
+++ b/GPy/models/FITC.py
@@ -7,7 +7,7 @@ from ..util.linalg import mdot, jitchol, chol_inv, tdot, symmetrify,pdinv
 from ..util.plot import gpplot
 from .. import kern
 from scipy import stats, linalg
-from sparse_GP import sparse_GP
+from ..core import sparse_GP
 
 def backsub_both_sides(L,X):
     """ Return L^-T * X * L^-1, assumuing X is symmetrical and L is lower cholesky"""
@@ -16,6 +16,9 @@ def backsub_both_sides(L,X):
 
 class FITC(sparse_GP):
 
+    def __init__(self, X, likelihood, kernel, Z, X_variance=None, normalize_X=False):
+        super(FITC, self).__init__(X, likelihood, kernel, normalize_X=normalize_X)
+
     def update_likelihood_approximation(self):
         """
         Approximates a non-gaussian likelihood using Expectation Propagation
diff --git a/GPy/models/GP.py b/GPy/models/GP.py
deleted file mode 100644
index e6c4c1d6..00000000
--- a/GPy/models/GP.py
+++ /dev/null
@@ -1,288 +0,0 @@
-# Copyright (c) 2012, GPy authors (see AUTHORS.txt).
-# Licensed under the BSD 3-clause license (see LICENSE.txt)
-
-
-import numpy as np
-from scipy import linalg
-import pylab as pb
-from .. import kern
-from ..core import model
-from ..util.linalg import pdinv, mdot, tdot
-from ..util.plot import gpplot, x_frame1D, x_frame2D, Tango
-from ..likelihoods import EP
-
-class GP(model):
-    """
-    Gaussian Process model for regression and EP
-
-    :param X: input observations
-    :param kernel: a GPy kernel, defaults to rbf+white
-    :parm likelihood: a GPy likelihood
-    :param normalize_X:  whether to normalize the input data before computing (predictions will be in original scales)
-    :type normalize_X: False|True
-    :rtype: model object
-    :param epsilon_ep: convergence criterion for the Expectation Propagation algorithm, defaults to 0.1
-    :param powerep: power-EP parameters [$\eta$,$\delta$], defaults to [1.,1.]
-    :type powerep: list
-
-    .. Note:: Multiple independent outputs are allowed using columns of Y
-
-    """
-    def __init__(self, X, likelihood, kernel, normalize_X=False):
-
-        # parse arguments
-        self.X = X
-        assert len(self.X.shape) == 2
-        self.N, self.Q = self.X.shape
-        assert isinstance(kernel, kern.kern)
-        self.kern = kernel
-        self.likelihood = likelihood
-        assert self.X.shape[0] == self.likelihood.data.shape[0]
-        self.N, self.D = self.likelihood.data.shape
-
-        # here's some simple normalization for the inputs
-        if normalize_X:
-            self._Xmean = X.mean(0)[None, :]
-            self._Xstd = X.std(0)[None, :]
-            self.X = (X.copy() - self._Xmean) / self._Xstd
-            if hasattr(self, 'Z'):
-                self.Z = (self.Z - self._Xmean) / self._Xstd
-        else:
-            self._Xmean = np.zeros((1, self.X.shape[1]))
-            self._Xstd = np.ones((1, self.X.shape[1]))
-
-        if not hasattr(self,'has_uncertain_inputs'):
-            self.has_uncertain_inputs = False
-        model.__init__(self)
-
-    def dL_dZ(self):
-        """
-        TODO: one day we might like to learn Z by gradient methods?
-        """
-        #FIXME: this doesn;t live here.
-        return np.zeros_like(self.Z)
-
-    def _set_params(self, p):
-        self.kern._set_params_transformed(p[:self.kern.Nparam_transformed()])
-        self.likelihood._set_params(p[self.kern.Nparam_transformed():])
-
-        self.K = self.kern.K(self.X)
-        self.K += self.likelihood.covariance_matrix
-
-        self.Ki, self.L, self.Li, self.K_logdet = pdinv(self.K)
-
-        # the gradient of the likelihood wrt the covariance matrix
-        if self.likelihood.YYT is None:
-            #alpha = np.dot(self.Ki, self.likelihood.Y)
-            alpha,_ = linalg.lapack.flapack.dpotrs(self.L, self.likelihood.Y,lower=1)
-
-            self.dL_dK = 0.5 * (tdot(alpha) - self.D * self.Ki)
-        else:
-            #tmp = mdot(self.Ki, self.likelihood.YYT, self.Ki)
-            tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(self.likelihood.YYT), lower=1)
-            tmp, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(tmp.T), lower=1)
-            self.dL_dK = 0.5 * (tmp - self.D * self.Ki)
-
-    def _get_params(self):
-        return np.hstack((self.kern._get_params_transformed(), self.likelihood._get_params()))
-
-    def _get_param_names(self):
-        return self.kern._get_param_names_transformed() + self.likelihood._get_param_names()
-
-    def update_likelihood_approximation(self):
-        """
-        Approximates a non-gaussian likelihood using Expectation Propagation
-
-        For a Gaussian likelihood, no iteration is required:
-        this function does nothing
-        """
-        self.likelihood.fit_full(self.kern.K(self.X))
-        self._set_params(self._get_params())  # update the GP
-
-    def _model_fit_term(self):
-        """
-        Computes the model fit using YYT if it's available
-        """
-        if self.likelihood.YYT is None:
-            tmp, _ = linalg.lapack.flapack.dtrtrs(self.L, np.asfortranarray(self.likelihood.Y), lower=1)
-            return -0.5 * np.sum(np.square(tmp))
-            #return -0.5 * np.sum(np.square(np.dot(self.Li, self.likelihood.Y)))
-        else:
-            return -0.5 * np.sum(np.multiply(self.Ki, self.likelihood.YYT))
-
-    def log_likelihood(self):
-        """
-        The log marginal likelihood of the GP.
-
-        For an EP model,  can be written as the log likelihood of a regression
-        model for a new variable Y* = v_tilde/tau_tilde, with a covariance
-        matrix K* = K + diag(1./tau_tilde) plus a normalization term.
-        """
-        return -0.5 * self.D * self.K_logdet + self._model_fit_term() + self.likelihood.Z
-
-
-    def _log_likelihood_gradients(self):
-        """
-        The gradient of all parameters.
-
-        Note, we use the chain rule: dL_dtheta = dL_dK * d_K_dtheta
-        """
-        return np.hstack((self.kern.dK_dtheta(dL_dK=self.dL_dK, X=self.X), self.likelihood._gradients(partial=np.diag(self.dL_dK))))
-
-    def _raw_predict(self, _Xnew, which_parts='all', full_cov=False,stop=False):
-        """
-        Internal helper function for making predictions, does not account
-        for normalization or likelihood
-        """
-        Kx = self.kern.K(_Xnew,self.X,which_parts=which_parts).T
-        #KiKx = np.dot(self.Ki, Kx)
-        KiKx, _ = linalg.lapack.flapack.dpotrs(self.L, np.asfortranarray(Kx), lower=1)
-        mu = np.dot(KiKx.T, self.likelihood.Y)
-        if full_cov:
-            Kxx = self.kern.K(_Xnew, which_parts=which_parts)
-            var = Kxx - np.dot(KiKx.T, Kx)
-        else:
-            Kxx = self.kern.Kdiag(_Xnew, which_parts=which_parts)
-            var = Kxx - np.sum(np.multiply(KiKx, Kx), 0)
-            var = var[:, None]
-        if stop:
-            debug_this
-        return mu, var
-
-
-    def predict(self, Xnew, which_parts='all', full_cov=False):
-        """
-        Predict the function(s) at the new point(s) Xnew.
-
-        Arguments
-        ---------
-        :param Xnew: The points at which to make a prediction
-        :type Xnew: np.ndarray, Nnew x self.Q
-        :param which_parts:  specifies which outputs kernel(s) to use in prediction
-        :type which_parts: ('all', list of bools)
-        :param full_cov: whether to return the folll covariance matrix, or just the diagonal
-        :type full_cov: bool
-        :rtype: posterior mean,  a Numpy array, Nnew x self.D
-        :rtype: posterior variance, a Numpy array, Nnew x 1 if full_cov=False, Nnew x Nnew otherwise
-        :rtype: lower and upper boundaries of the 95% confidence intervals, Numpy arrays,  Nnew x self.D
-
-
-           If full_cov and self.D > 1, the return shape of var is Nnew x Nnew x self.D. If self.D == 1, the return shape is Nnew x Nnew.
-           This is to allow for different normalizations of the output dimensions.
-
-        """
-        # normalize X values
-        Xnew = (Xnew.copy() - self._Xmean) / self._Xstd
-        mu, var = self._raw_predict(Xnew, full_cov=full_cov, which_parts=which_parts)
-
-        # now push through likelihood
-        mean, var, _025pm, _975pm = self.likelihood.predictive_values(mu, var, full_cov)
-
-        return mean, var, _025pm, _975pm
-
-
-    def plot_f(self, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, full_cov=False):
-        """
-        Plot the GP's view of the world, where the data is normalized and the
-        likelihood is Gaussian.
-
-        :param samples: the number of a posteriori samples to plot
-        :param which_data: which if the training data to plot (default all)
-        :type which_data: 'all' or a slice object to slice self.X, self.Y
-        :param plot_limits: The limits of the plot. If 1D [xmin,xmax], if 2D [[xmin,ymin],[xmax,ymax]]. Defaluts to data limits
-        :param which_parts: which of the kernel functions to plot (additively)
-        :type which_parts: 'all', or list of bools
-        :param resolution: the number of intervals to sample the GP on. Defaults to 200 in 1D and 50 (a 50x50 grid) in 2D
-
-        Plot the posterior of the GP.
-          - In one dimension, the function is plotted with a shaded region identifying two standard deviations.
-          - In two dimsensions, a contour-plot shows the mean predicted function
-          - In higher dimensions, we've no implemented this yet !TODO!
-
-        Can plot only part of the data and part of the posterior functions
-        using which_data and which_functions
-        """
-        if which_data == 'all':
-            which_data = slice(None)
-
-        if self.X.shape[1] == 1:
-            Xnew, xmin, xmax = x_frame1D(self.X, plot_limits=plot_limits)
-            if samples == 0:
-                m, v = self._raw_predict(Xnew, which_parts=which_parts)
-                gpplot(Xnew, m, m - 2 * np.sqrt(v), m + 2 * np.sqrt(v))
-                pb.plot(self.X[which_data], self.likelihood.Y[which_data], 'kx', mew=1.5)
-            else:
-                m, v = self._raw_predict(Xnew, which_parts=which_parts, full_cov=True)
-                Ysim = np.random.multivariate_normal(m.flatten(), v, samples)
-                gpplot(Xnew, m, m - 2 * np.sqrt(np.diag(v)[:, None]), m + 2 * np.sqrt(np.diag(v))[:, None])
-                for i in range(samples):
-                    pb.plot(Xnew, Ysim[i, :], Tango.colorsHex['darkBlue'], linewidth=0.25)
-            pb.plot(self.X[which_data], self.likelihood.Y[which_data], 'kx', mew=1.5)
-            pb.xlim(xmin, xmax)
-            ymin, ymax = min(np.append(self.likelihood.Y, m - 2 * np.sqrt(np.diag(v)[:, None]))), max(np.append(self.likelihood.Y, m + 2 * np.sqrt(np.diag(v)[:, None])))
-            ymin, ymax = ymin - 0.1 * (ymax - ymin), ymax + 0.1 * (ymax - ymin)
-            pb.ylim(ymin, ymax)
-            if hasattr(self, 'Z'):
-                pb.plot(self.Z, self.Z * 0 + pb.ylim()[0], 'r|', mew=1.5, markersize=12)
-
-        elif self.X.shape[1] == 2:
-            resolution = resolution or 50
-            Xnew, xmin, xmax, xx, yy = x_frame2D(self.X, plot_limits, resolution)
-            m, v = self._raw_predict(Xnew, which_parts=which_parts)
-            m = m.reshape(resolution, resolution).T
-            pb.contour(xx, yy, m, vmin=m.min(), vmax=m.max(), cmap=pb.cm.jet)
-            pb.scatter(Xorig[:, 0], Xorig[:, 1], 40, Yorig, linewidth=0, cmap=pb.cm.jet, vmin=m.min(), vmax=m.max())
-            pb.xlim(xmin[0], xmax[0])
-            pb.ylim(xmin[1], xmax[1])
-        else:
-            raise NotImplementedError, "Cannot define a frame with more than two input dimensions"
-
-    def plot(self, samples=0, plot_limits=None, which_data='all', which_parts='all', resolution=None, levels=20):
-        """
-        TODO: Docstrings!
-        :param levels: for 2D plotting, the number of contour levels to use
-
-        """
-        # TODO include samples
-        if which_data == 'all':
-            which_data = slice(None)
-
-        if self.X.shape[1] == 1:
-
-            Xu = self.X * self._Xstd + self._Xmean  # NOTE self.X are the normalized values now
-
-            Xnew, xmin, xmax = x_frame1D(Xu, plot_limits=plot_limits)
-            m, var, lower, upper = self.predict(Xnew, which_parts=which_parts)
-            for d in range(m.shape[1]):
-                gpplot(Xnew, m[:,d], lower[:,d], upper[:,d])
-                pb.plot(Xu[which_data], self.likelihood.data[which_data,d], 'kx', mew=1.5)
-            if self.has_uncertain_inputs:
-                pb.errorbar(Xu[which_data, 0], self.likelihood.data[which_data, 0],
-                            xerr=2 * np.sqrt(self.X_variance[which_data, 0]),
-                            ecolor='k', fmt=None, elinewidth=.5, alpha=.5)
-
-            ymin, ymax = min(np.append(self.likelihood.data, lower)), max(np.append(self.likelihood.data, upper))
-            ymin, ymax = ymin - 0.1 * (ymax - ymin), ymax + 0.1 * (ymax - ymin)
-            pb.xlim(xmin, xmax)
-            pb.ylim(ymin, ymax)
-            if hasattr(self, 'Z'):
-                Zu = self.Z * self._Xstd + self._Xmean
-                pb.plot(Zu, Zu * 0 + pb.ylim()[0], 'r|', mew=1.5, markersize=12)
-                    # pb.errorbar(self.X[:,0], pb.ylim()[0]+np.zeros(self.N), xerr=2*np.sqrt(self.X_variance.flatten()))
-
-        elif self.X.shape[1] == 2:  # FIXME
-            resolution = resolution or 50
-            Xnew, xx, yy, xmin, xmax = x_frame2D(self.X, plot_limits, resolution)
-            x, y = np.linspace(xmin[0], xmax[0], resolution), np.linspace(xmin[1], xmax[1], resolution)
-            m, var, lower, upper = self.predict(Xnew, which_parts=which_parts)
-            m = m.reshape(resolution, resolution).T
-            pb.contour(x, y, m, levels, vmin=m.min(), vmax=m.max(), cmap=pb.cm.jet)
-            Yf = self.likelihood.Y.flatten()
-            pb.scatter(self.X[:, 0], self.X[:, 1], 40, Yf, cmap=pb.cm.jet, vmin=m.min(), vmax=m.max(), linewidth=0.)
-            pb.xlim(xmin[0], xmax[0])
-            pb.ylim(xmin[1], xmax[1])
-            if hasattr(self, 'Z'):
-                pb.plot(self.Z[:, 0], self.Z[:, 1], 'wo')
-
-        else:
-            raise NotImplementedError, "Cannot define a frame with more than two input dimensions"
diff --git a/GPy/models/GPLVM.py b/GPy/models/GPLVM.py
index 7445d0ab..5d89527b 100644
--- a/GPy/models/GPLVM.py
+++ b/GPy/models/GPLVM.py
@@ -8,7 +8,7 @@ import sys, pdb
 from .. import kern
 from ..core import model
 from ..util.linalg import pdinv, PCA
-from GP import GP
+from ..core import GP
 from ..likelihoods import Gaussian
 from .. import util
 from GPy.util import plot_latent
@@ -32,7 +32,8 @@ class GPLVM(GP):
         if kernel is None:
             kernel = kern.rbf(Q, ARD=Q>1) + kern.bias(Q, np.exp(-2)) + kern.white(Q, np.exp(-2))
         likelihood = Gaussian(Y, normalize=normalize_Y)
-        GP.__init__(self, X, likelihood, kernel, **kwargs)
+        super(GPLVM, self).__init__(self, X, likelihood, kernel, **kwargs)
+        self._set_params(self._get_params())
 
     def initialise_latent(self, init, Q, Y):
         if init == 'PCA':
@@ -63,4 +64,4 @@ class GPLVM(GP):
         pb.plot(mu[:,0], mu[:,1],'k',linewidth=1.5)
 
     def plot_latent(self, *args, **kwargs):
-        util.plot_latent.plot_latent(self, *args, **kwargs)
\ No newline at end of file
+        util.plot_latent.plot_latent(self, *args, **kwargs)
diff --git a/GPy/models/GP_regression.py b/GPy/models/GP_regression.py
index 7f2673a6..2979456b 100644
--- a/GPy/models/GP_regression.py
+++ b/GPy/models/GP_regression.py
@@ -3,7 +3,7 @@
 
 
 import numpy as np
-from GP import GP
+from ..core import GP
 from .. import likelihoods
 from .. import kern
 
@@ -31,4 +31,5 @@ class GP_regression(GP):
 
         likelihood = likelihoods.Gaussian(Y,normalize=normalize_Y)
 
-        GP.__init__(self, X, likelihood, kernel, normalize_X=normalize_X)
+        super(GP_regression, self).__init__(self, X, likelihood, kernel, normalize_X=normalize_X)
+        self._set_params(self._get_params())
diff --git a/GPy/models/__init__.py b/GPy/models/__init__.py
index 7cacffb1..700ea120 100644
--- a/GPy/models/__init__.py
+++ b/GPy/models/__init__.py
@@ -2,9 +2,9 @@
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 
 
-from GP import GP
+#from GP import GP
+#from sparse_GP import sparse_GP
 from GP_regression import GP_regression
-from sparse_GP import sparse_GP
 from sparse_GP_regression import sparse_GP_regression
 from GPLVM import GPLVM
 from warped_GP import warpedGP
diff --git a/GPy/models/generalized_FITC.py b/GPy/models/generalized_FITC.py
index 966cbd39..514a35a1 100644
--- a/GPy/models/generalized_FITC.py
+++ b/GPy/models/generalized_FITC.py
@@ -7,7 +7,7 @@ from ..util.linalg import mdot, jitchol, chol_inv, pdinv, trace_dot
 from ..util.plot import gpplot
 from .. import kern
 from scipy import stats, linalg
-from sparse_GP import sparse_GP
+from ..core import sparse_GP
 
 def backsub_both_sides(L,X):
     """ Return L^-T * X * L^-1, assumuing X is symmetrical and L is lower cholesky"""
@@ -36,12 +36,12 @@ class generalized_FITC(sparse_GP):
     """
 
     def __init__(self, X, likelihood, kernel, Z, X_variance=None, normalize_X=False):
-
         self.Z = Z
         self.M = self.Z.shape[0]
         self.true_precision = likelihood.precision
 
-        sparse_GP.__init__(self, X, likelihood, kernel=kernel, Z=self.Z, X_variance=None, normalize_X=False)
+        super(generalized_FITC, self).__init__(self, X, likelihood, kernel=kernel, Z=self.Z, X_variance=None, normalize_X=False)
+        self._set_params(self._get_params())
 
     def _set_params(self, p):
         self.Z = p[:self.M*self.Q].reshape(self.M, self.Q)
diff --git a/GPy/models/mrd.py b/GPy/models/mrd.py
index 89b5d730..88930040 100644
--- a/GPy/models/mrd.py
+++ b/GPy/models/mrd.py
@@ -5,7 +5,7 @@ Created on 10 Apr 2013
 '''
 from GPy.core import model
 from GPy.models.Bayesian_GPLVM import Bayesian_GPLVM
-from GPy.models.sparse_GP import sparse_GP
+from GPy.core import sparse_GP
 from GPy.util.linalg import PCA
 from scipy import linalg
 import numpy
@@ -23,7 +23,7 @@ class MRD(model):
     :type likelihood_list: [GPy.likelihood] | [Y1..Yy]
     :param names: names for different gplvm models
     :type names: [str]
-    :param Q: latent dimensionality (will raise 
+    :param Q: latent dimensionality (will raise
     :type Q: int
     :param initx: initialisation method for the latent space
     :type initx: 'PCA'|'random'
@@ -77,6 +77,7 @@ class MRD(model):
         self.MQ = self.M * self.Q
 
         model.__init__(self) # @UndefinedVariable
+        self._set_params(self._get_params())
 
     @property
     def X(self):
@@ -153,7 +154,7 @@ class MRD(model):
     def _get_params(self):
         """
         return parameter list containing private and shared parameters as follows:
-        
+
         =================================================================
         | mu | S | Z || theta1 | theta2 | .. | thetaN |
         =================================================================
diff --git a/GPy/models/sparse_GPLVM.py b/GPy/models/sparse_GPLVM.py
index 591c49b2..af388f1c 100644
--- a/GPy/models/sparse_GPLVM.py
+++ b/GPy/models/sparse_GPLVM.py
@@ -8,7 +8,7 @@ import sys, pdb
 # from .. import kern
 # from ..core import model
 # from ..util.linalg import pdinv, PCA
-from GPLVM import GPLVM
+from ..core import GPLVM
 from sparse_GP_regression import sparse_GP_regression
 
 class sparse_GPLVM(sparse_GP_regression, GPLVM):
diff --git a/GPy/models/sparse_GP_regression.py b/GPy/models/sparse_GP_regression.py
index 84a5d37c..d90ead3d 100644
--- a/GPy/models/sparse_GP_regression.py
+++ b/GPy/models/sparse_GP_regression.py
@@ -3,7 +3,7 @@
 
 
 import numpy as np
-from sparse_GP import sparse_GP
+from ..core import sparse_GP
 from .. import likelihoods
 from .. import kern
 from ..likelihoods import likelihood
@@ -43,4 +43,5 @@ class sparse_GP_regression(sparse_GP):
         #likelihood defaults to Gaussian
         likelihood = likelihoods.Gaussian(Y,normalize=normalize_Y)
 
-        sparse_GP.__init__(self, X, likelihood, kernel, Z, normalize_X=normalize_X)
+        super(sparse_GP_regression, self).__init__(self, X, likelihood, kernel, Z, normalize_X=normalize_X)
+        self._set_params(self._get_params())
diff --git a/GPy/models/warped_GP.py b/GPy/models/warped_GP.py
index 64d0b541..8e67b551 100644
--- a/GPy/models/warped_GP.py
+++ b/GPy/models/warped_GP.py
@@ -9,7 +9,7 @@ from ..util.linalg import pdinv
 from ..util.plot import gpplot
 from ..util.warping_functions import *
 from GP_regression import GP_regression
-from GP import GP
+from ..core import GP
 from .. import likelihoods
 from .. import kern
 
@@ -29,7 +29,8 @@ class warpedGP(GP):
         self.predict_in_warped_space = False
         likelihood = likelihoods.Gaussian(self.transform_data(), normalize=normalize_Y)
 
-        GP.__init__(self, X, likelihood, kernel, normalize_X=normalize_X)
+        super(warpedGP, self).__init__(self, X, likelihood, kernel, normalize_X=normalize_X)
+        self._set_params(self._get_params())
 
     def _scale_data(self, Y):
         self._Ymax = Y.max()