diff --git a/GPy/core/model.py b/GPy/core/model.py
index c067d51d..21bcf0c7 100644
--- a/GPy/core/model.py
+++ b/GPy/core/model.py
@@ -485,20 +485,17 @@ class Model(Parameterized):
         if not hasattr(self, 'kern'):
             raise ValueError, "this model has no kernel"
 
-        k = [p for p in self.kern._parameters_ if hasattr(p, "ARD") and p.ARD]
-        if (not len(k) == 1):
-            raise ValueError, "cannot determine sensitivity for this kernel"
-        k = k[0]
-        from ..kern.parts.rbf import RBF
-        from ..kern.parts.rbf_inv import RBFInv
-        from ..kern.parts.linear import Linear
+        k = self.kern#[p for p in self.kern._parameters_ if hasattr(p, "ARD") and p.ARD]
+        from ..kern import RBF, Linear#, RBFInv
+
         if isinstance(k, RBF):
             return 1. / k.lengthscale
-        elif isinstance(k, RBFInv):
-            return k.inv_lengthscale
+        #elif isinstance(k, RBFInv):
+        #    return k.inv_lengthscale
         elif isinstance(k, Linear):
             return k.variances
-
+        else:
+            raise ValueError, "cannot determine sensitivity for this kernel"
 
     def pseudo_EM(self, stop_crit=.1, **kwargs):
         """
diff --git a/GPy/core/parameterization/index_operations.py b/GPy/core/parameterization/index_operations.py
index bfd0bf21..b5399741 100644
--- a/GPy/core/parameterization/index_operations.py
+++ b/GPy/core/parameterization/index_operations.py
@@ -83,11 +83,21 @@ class ParameterIndexOperations(object):
     def iterproperties(self):
         return self._properties.iterkeys()
     
-    def shift(self, start, size):
+    def shift_right(self, start, size):
         for ind in self.iterindices():
             toshift = ind>=start
-            if toshift.size > 0:
-                ind[toshift] += size
+            ind[toshift] += size
+
+    def shift_left(self, start, size):
+        for v, ind in self.items():
+            todelete = (ind>=start) * (ind<start+size)
+            if todelete.size != 0:
+                ind = ind[~todelete]
+            toshift = ind>=start
+            if toshift.size != 0:
+                ind[toshift] -= size
+            if ind.size != 0: self._properties[v] = ind
+            else: del self._properties[v]
     
     def clear(self):
         self._properties.clear()
@@ -183,7 +193,7 @@ class ParameterIndexOperationsView(object):
             yield i 
 
 
-    def shift(self, start, size):
+    def shift_right(self, start, size):
         raise NotImplementedError, 'Shifting only supported in original ParamIndexOperations'
     
 
diff --git a/GPy/core/parameterization/parameter_core.py b/GPy/core/parameterization/parameter_core.py
index 45b57eab..c2c8a05a 100644
--- a/GPy/core/parameterization/parameter_core.py
+++ b/GPy/core/parameterization/parameter_core.py
@@ -390,6 +390,7 @@ class Parameterizable(Constrainable):
         import copy
         from .index_operations import ParameterIndexOperations, ParameterIndexOperationsView
         from .array_core import ParamList
+
         dc = dict()
         for k, v in self.__dict__.iteritems():
             if k not in ['_direct_parent_', '_parameters_', '_parent_index_'] + self.parameter_names():
@@ -399,18 +400,21 @@ class Parameterizable(Constrainable):
                     dc[k] = copy.deepcopy(v)
             if k == '_parameters_':
                 params = [p.copy() for p in v]
-        # dc = copy.deepcopy(self.__dict__)
+        
         dc['_direct_parent_'] = None
         dc['_parent_index_'] = None
         dc['_parameters_'] = ParamList()
+        dc['constraints'].clear()
+        dc['priors'].clear()
+        dc['size'] = 0
+
         s = self.__new__(self.__class__)
         s.__dict__ = dc
-        # import ipdb;ipdb.set_trace()
+        
         for p in params:
             s.add_parameter(p)
-        # dc._notify_parent_change()
+        
         return s
-        # return copy.deepcopy(self)
 
     def _notify_parameters_changed(self):
         self.parameters_changed()
diff --git a/GPy/core/parameterization/parameterized.py b/GPy/core/parameterization/parameterized.py
index 177cc217..d463ed43 100644
--- a/GPy/core/parameterization/parameterized.py
+++ b/GPy/core/parameterization/parameterized.py
@@ -87,8 +87,8 @@ class Parameterized(Parameterizable, Pickleable, Observable, Gradcheckable):
                 self._parameters_.append(param)
             else:
                 start = sum(p.size for p in self._parameters_[:index])
-                self.constraints.shift(start, param.size)
-                self.priors.shift(start, param.size)
+                self.constraints.shift_right(start, param.size)
+                self.priors.shift_right(start, param.size)
                 self.constraints.update(param.constraints, start)
                 self.priors.update(param.priors, start)
                 self._parameters_.insert(index, param)
@@ -113,15 +113,19 @@ class Parameterized(Parameterizable, Pickleable, Observable, Gradcheckable):
         """
         if not param in self._parameters_:
             raise RuntimeError, "Parameter {} does not belong to this object, remove parameters directly from their respective parents".format(param._short())
-        del self._parameters_[param._parent_index_]
+        
+        start = sum([p.size for p in self._parameters_[:param._parent_index_]])
+        self._remove_parameter_name(param)
         self.size -= param.size
+        del self._parameters_[param._parent_index_]
         
         param._disconnect_parent()
-        self._remove_parameter_name(param)
-        
-        #self._notify_parent_change()
+        self.constraints.shift_left(start, param.size)
         self._connect_fixes()
-
+        self._connect_parameters()
+        self._notify_parent_change()
+        
+        
     def _connect_parameters(self):
         # connect parameterlist to this parameterized object
         # This just sets up the right connection for the params objects
diff --git a/GPy/core/parameterization/variational.py b/GPy/core/parameterization/variational.py
index a7b26a80..5fe63052 100644
--- a/GPy/core/parameterization/variational.py
+++ b/GPy/core/parameterization/variational.py
@@ -29,3 +29,29 @@ class Normal(Parameterized):
         assert "matplotlib" in sys.modules, "matplotlib package has not been imported."
         from ...plotting.matplot_dep import variational_plots
         return variational_plots.plot(self,*args)
+
+
+class SpikeAndSlab(Parameterized):
+    '''
+    The SpikeAndSlab distribution for variational approximations.
+    '''
+    def __init__(self, means, variances, binary_prob, name='latent space'):
+        """
+        binary_prob : the probability of the distribution on the slab part.
+        """
+        Parameterized.__init__(self, name=name)
+        self.mean = Param("mean", means)
+        self.variance = Param('variance', variances, Logexp())
+        self.gamma = Param("binary_prob",binary_prob,)
+        self.add_parameters(self.mean, self.variance, self.gamma)
+
+    def plot(self, *args):
+        """
+        Plot latent space X in 1D:
+
+        See  GPy.plotting.matplot_dep.variational_plots
+        """
+        import sys
+        assert "matplotlib" in sys.modules, "matplotlib package has not been imported."
+        from ...plotting.matplot_dep import variational_plots
+        return variational_plots.plot(self,*args)
diff --git a/GPy/core/sparse_gp.py b/GPy/core/sparse_gp.py
index 61a664fe..71053867 100644
--- a/GPy/core/sparse_gp.py
+++ b/GPy/core/sparse_gp.py
@@ -57,11 +57,14 @@ class SparseGP(GP):
         return not (self.X_variance is None)                
 
     def parameters_changed(self):
-        self.posterior, self._log_marginal_likelihood, self.grad_dict = self.inference_method.inference(self.kern, self.X, self.X_variance, self.Z, self.likelihood, self.Y)
+        if self.has_uncertain_inputs():
+            self.posterior, self._log_marginal_likelihood, self.grad_dict = self.inference_method.inference_latent(self.kern, self.q, self.Z, self.likelihood, self.Y)
+        else:
+            self.posterior, self._log_marginal_likelihood, self.grad_dict = self.inference_method.inference(self.kern, self.X, self.X_variance, self.Z, self.likelihood, self.Y)
         self.likelihood.update_gradients(self.grad_dict.pop('partial_for_likelihood'))
         if self.has_uncertain_inputs():
-            self.kern.update_gradients_variational(mu=self.X, S=self.X_variance, Z=self.Z, **self.grad_dict)
-            self.Z.gradient = self.kern.gradients_Z_variational(mu=self.X, S=self.X_variance, Z=self.Z, **self.grad_dict)
+            self.kern.update_gradients_variational(posterior_variational=self.q, Z=self.Z, **self.grad_dict)
+            self.Z.gradient = self.kern.gradients_Z_variational(posterior_variational=self.q, Z=self.Z, **self.grad_dict)
         else:
             self.kern.update_gradients_sparse(X=self.X, Z=self.Z, **self.grad_dict)
             self.Z.gradient = self.kern.gradients_Z_sparse(X=self.X, Z=self.Z, **self.grad_dict)
diff --git a/GPy/examples/dimensionality_reduction.py b/GPy/examples/dimensionality_reduction.py
index c8e79e6c..3ba54d34 100644
--- a/GPy/examples/dimensionality_reduction.py
+++ b/GPy/examples/dimensionality_reduction.py
@@ -74,7 +74,7 @@ def gplvm_oil_100(optimize=True, verbose=1, plot=True):
     data = GPy.util.datasets.oil_100()
     Y = data['X']
     # create simple GP model
-    kernel = GPy.kern.RBF(6, ARD=True) + GPy.kern.bias(6)
+    kernel = GPy.kern.RBF(6, ARD=True) + GPy.kern.Bias(6)
     m = GPy.models.GPLVM(Y, 6, kernel=kernel)
     m.data_labels = data['Y'].argmax(axis=1)
     if optimize: m.optimize('scg', messages=verbose)
@@ -190,17 +190,22 @@ def _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim=False):
     _np.random.seed(1234)
     
     x = _np.linspace(0, 4 * _np.pi, N)[:, None]
-    s1 = _np.vectorize(lambda x: _np.sin(x))
+    s1 = _np.vectorize(lambda x: -_np.sin(x))
     s2 = _np.vectorize(lambda x: _np.cos(x))
     s3 = _np.vectorize(lambda x:-_np.exp(-_np.cos(2 * x)))
-    sS = _np.vectorize(lambda x: _np.sin(2 * x))
+    sS = _np.vectorize(lambda x: x*_np.sin(x))
 
     s1 = s1(x)
     s2 = s2(x)
     s3 = s3(x)
     sS = sS(x)
 
-    S1 = _np.hstack([s1, sS])
+    s1 -= s1.mean(); s1 /= s1.std(0)
+    s2 -= s2.mean(); s2 /= s2.std(0)
+    s3 -= s3.mean(); s3 /= s3.std(0)
+    sS -= sS.mean(); sS /= sS.std(0)
+
+    S1 = _np.hstack([s1, s2, sS])
     S2 = _np.hstack([s2, s3, sS])
     S3 = _np.hstack([s3, sS])
 
@@ -271,7 +276,7 @@ def bgplvm_simulation(optimize=True, verbose=1,
     D1, D2, D3, N, num_inducing, Q = 15, 5, 8, 30, 3, 10
     _, _, Ylist = _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim)
     Y = Ylist[0]
-    k = kern.linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
+    k = kern.Linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
     m = BayesianGPLVM(Y, Q, init="PCA", num_inducing=num_inducing, kernel=k)
     
     if optimize:
@@ -291,10 +296,10 @@ def bgplvm_simulation_missing_data(optimize=True, verbose=1,
     from GPy.models import BayesianGPLVM
     from GPy.inference.latent_function_inference.var_dtc import VarDTCMissingData
 
-    D1, D2, D3, N, num_inducing, Q = 15, 5, 8, 30, 3, 10
+    D1, D2, D3, N, num_inducing, Q = 15, 5, 8, 30, 5, 9
     _, _, Ylist = _simulate_sincos(D1, D2, D3, N, num_inducing, Q, plot_sim)
     Y = Ylist[0]
-    k = kern.linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
+    k = kern.Linear(Q, ARD=True)# + kern.white(Q, _np.exp(-2)) # + kern.bias(Q)
     
     inan = _np.random.binomial(1, .6, size=Y.shape).astype(bool)
     m = BayesianGPLVM(Y.copy(), Q, init="random", num_inducing=num_inducing, kernel=k)
diff --git a/GPy/inference/latent_function_inference/var_dtc.py b/GPy/inference/latent_function_inference/var_dtc.py
index a81bb711..349cd72d 100644
--- a/GPy/inference/latent_function_inference/var_dtc.py
+++ b/GPy/inference/latent_function_inference/var_dtc.py
@@ -43,9 +43,20 @@ class VarDTC(object):
         return Y * prec # TODO chache this, and make it effective
     
     def inference(self, kern, X, X_variance, Z, likelihood, Y):
+        """Inference for normal sparseGP"""
+        uncertain_inputs = False
+        psi0, psi1, psi2 = _compute_psi(kern, X, X_variance, Z, uncertain_inputs)
+        return self._inference(kern, psi0, psi1, psi2, Z, likelihood, Y, uncertain_inputs)
+
+    def inference_latent(self, kern, posterior_variational, Z, likelihood, Y):
+        """Inference for GPLVM with uncertain inputs"""
+        uncertain_inputs = True
+        psi0, psi1, psi2 = _compute_psi_latent(kern, posterior_variational, Z)
+        return self._inference(kern, psi0, psi1, psi2, Z, likelihood, Y, uncertain_inputs)
+    
+    def _inference(self, kern, psi0, psi1, psi2, Z, likelihood, Y, uncertain_inputs):
 
         #see whether we're using variational uncertain inputs
-        uncertain_inputs = not (X_variance is None)
         
         _, output_dim = Y.shape
         
@@ -62,10 +73,9 @@ class VarDTC(object):
         # do the inference:
         het_noise = beta.size < 1
         num_inducing = Z.shape[0]
-        num_data = X.shape[0]
+        num_data = Y.shape[0]
         # kernel computations, using BGPLVM notation
-        Kmm = kern.K(Z)
-        psi0, psi1, psi2 = _compute_psi(kern, X, X_variance, Z, uncertain_inputs) 
+        Kmm = kern.K(Z) 
         
         Lm = jitchol(Kmm)
         
@@ -191,20 +201,31 @@ class VarDTCMissingData(object):
         else:
             self._subarray_indices = [[slice(None),slice(None)]]
             return [Y], [(Y**2).sum()]
-    
+
     def inference(self, kern, X, X_variance, Z, likelihood, Y):
+        """Inference for normal sparseGP"""
+        uncertain_inputs = False
+        psi0, psi1, psi2 = _compute_psi(kern, X, X_variance, Z, uncertain_inputs)
+        return self._inference(kern, psi0, psi1, psi2, Z, likelihood, Y, uncertain_inputs)
+
+    def inference_latent(self, kern, posterior_variational, Z, likelihood, Y):
+        """Inference for GPLVM with uncertain inputs"""
+        uncertain_inputs = True
+        psi0, psi1, psi2 = _compute_psi_latent(kern, posterior_variational, Z)
+        return self._inference(kern, psi0, psi1, psi2, Z, likelihood, Y, uncertain_inputs)
+    
+    def _inference(self, kern, psi0_all, psi1_all, psi2_all, Z, likelihood, Y, uncertain_inputs):
         Ys, traces = self._Y(Y)
         beta_all = 1./likelihood.variance
-        uncertain_inputs = not (X_variance is None)
         het_noise = beta_all.size != 1
 
         import itertools
         num_inducing = Z.shape[0]
 
-        dL_dpsi0_all = np.zeros(X.shape[0])
-        dL_dpsi1_all = np.zeros((X.shape[0], num_inducing))
+        dL_dpsi0_all = np.zeros(Y.shape[0])
+        dL_dpsi1_all = np.zeros((Y.shape[0], num_inducing))
         if uncertain_inputs:
-            dL_dpsi2_all = np.zeros((X.shape[0], num_inducing, num_inducing))
+            dL_dpsi2_all = np.zeros((Y.shape[0], num_inducing, num_inducing))
         
         partial_for_likelihood = 0
         woodbury_vector = np.zeros((num_inducing, Y.shape[1]))
@@ -217,9 +238,6 @@ class VarDTCMissingData(object):
         Lm = jitchol(Kmm)
         if uncertain_inputs: LmInv = dtrtri(Lm)
 
-        # kernel computations, using BGPLVM notation
-        psi0_all, psi1_all, psi2_all = _compute_psi(kern, X, X_variance, Z, uncertain_inputs)
-
         VVT_factor_all = np.empty(Y.shape)
         full_VVT_factor = VVT_factor_all.shape[1] == Y.shape[1]
         if not full_VVT_factor:
@@ -308,14 +326,14 @@ class VarDTCMissingData(object):
         # gradients:
         if uncertain_inputs:
             grad_dict = {'dL_dKmm': dL_dKmm, 
-                         'dL_dpsi0':dL_dpsi0, 
-                         'dL_dpsi1':dL_dpsi1, 
-                         'dL_dpsi2':dL_dpsi2, 
+                         'dL_dpsi0':dL_dpsi0_all, 
+                         'dL_dpsi1':dL_dpsi1_all, 
+                         'dL_dpsi2':dL_dpsi2_all, 
                          'partial_for_likelihood':partial_for_likelihood}
         else:
             grad_dict = {'dL_dKmm': dL_dKmm, 
-                         'dL_dKdiag':dL_dpsi0, 
-                         'dL_dKnm':dL_dpsi1, 
+                         'dL_dKdiag':dL_dpsi0_all, 
+                         'dL_dKnm':dL_dpsi1_all, 
                          'partial_for_likelihood':partial_for_likelihood}
 
         #get sufficient things for posterior prediction
@@ -340,15 +358,16 @@ class VarDTCMissingData(object):
         return post, log_marginal, grad_dict
 
 
-def _compute_psi(kern, X, X_variance, Z, uncertain_inputs):
-    if uncertain_inputs:
-        psi0 = kern.psi0(Z, X, X_variance)
-        psi1 = kern.psi1(Z, X, X_variance)
-        psi2 = kern.psi2(Z, X, X_variance)
-    else:
-        psi0 = kern.Kdiag(X)
-        psi1 = kern.K(X, Z)
-        psi2 = None
+def _compute_psi(kern, X, X_variance, Z):
+    psi0 = kern.Kdiag(X)
+    psi1 = kern.K(X, Z)
+    psi2 = None
+    return psi0, psi1, psi2
+
+def _compute_psi_latent(kern, posterior_variational, Z):
+    psi0 = kern.psi0(Z, posterior_variational)
+    psi1 = kern.psi1(Z, posterior_variational)
+    psi2 = kern.psi2(Z, posterior_variational)
     return psi0, psi1, psi2
 
 def _compute_dL_dpsi(num_inducing, num_data, output_dim, beta, Lm, VVT_factor, Cpsi1Vf, DBi_plus_BiPBi, psi1, het_noise, uncertain_inputs):
diff --git a/GPy/kern/_src/kern.py b/GPy/kern/_src/kern.py
index b3ee57cd..3ef231b3 100644
--- a/GPy/kern/_src/kern.py
+++ b/GPy/kern/_src/kern.py
@@ -26,11 +26,11 @@ class Kern(Parameterized):
         raise NotImplementedError
     def Kdiag(self, Xa):
         raise NotImplementedError
-    def psi0(self,Z,mu,S):
+    def psi0(self,Z,posterior_variational):
         raise NotImplementedError
-    def psi1(self,Z,mu,S):
+    def psi1(self,Z,posterior_variational):
         raise NotImplementedError
-    def psi2(self,Z,mu,S):
+    def psi2(self,Z,posterior_variational):
         raise NotImplementedError
     def gradients_X(self, dL_dK, X, X2):
         raise NotImplementedError
@@ -49,16 +49,16 @@ class Kern(Parameterized):
         self._collect_gradient(target)
         self._set_gradient(target)
 
-    def update_gradients_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def update_gradients_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
         """Set the gradients of all parameters when doing variational (M) inference with uncertain inputs."""
         raise NotImplementedError
     def gradients_Z_sparse(self, dL_dKmm, dL_dKnm, dL_dKdiag, X, Z):
         grad = self.gradients_X(dL_dKmm, Z)
         grad += self.gradients_X(dL_dKnm.T, Z, X)
         return grad
-    def gradients_Z_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def gradients_Z_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
         raise NotImplementedError
-    def gradients_muS_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def gradients_q_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
         raise NotImplementedError
     
     def plot_ARD(self, *args):
@@ -67,7 +67,7 @@ class Kern(Parameterized):
         See GPy.plotting.matplot_dep.plot_ARD
         """
         assert "matplotlib" in sys.modules, "matplotlib package has not been imported."
-        from ..plotting.matplot_dep import kernel_plots
+        from ...plotting.matplot_dep import kernel_plots
         return kernel_plots.plot_ARD(self,*args)
 
 
diff --git a/GPy/kern/_src/rbf.py b/GPy/kern/_src/rbf.py
index c4d595d0..0c8588a2 100644
--- a/GPy/kern/_src/rbf.py
+++ b/GPy/kern/_src/rbf.py
@@ -79,16 +79,21 @@ class RBF(Kern):
         ret[:] = self.variance
         return ret
 
-    def psi0(self, Z, mu, S):
+    def psi0(self, Z, posterior_variational):
+        mu = posterior_variational.mean
         ret = np.empty(mu.shape[0], dtype=np.float64)
         ret[:] = self.variance
         return ret
 
-    def psi1(self, Z, mu, S):
+    def psi1(self, Z, posterior_variational):
+        mu = posterior_variational.mean
+        S = posterior_variational.variance
         self._psi_computations(Z, mu, S)
         return self._psi1
 
-    def psi2(self, Z, mu, S):
+    def psi2(self, Z, posterior_variational):
+        mu = posterior_variational.mean
+        S = posterior_variational.variance
         self._psi_computations(Z, mu, S)
         return self._psi2
 
@@ -121,7 +126,9 @@ class RBF(Kern):
         else:
             self.lengthscale.gradient += (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dKmm)
 
-    def update_gradients_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def update_gradients_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
+        mu = posterior_variational.mean
+        S = posterior_variational.variance        
         self._psi_computations(Z, mu, S)
 
         #contributions from psi0:
@@ -155,7 +162,9 @@ class RBF(Kern):
         else:
             self.lengthscale.gradient += (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dKmm)
 
-    def gradients_Z_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def gradients_Z_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
+        mu = posterior_variational.mean
+        S = posterior_variational.variance
         self._psi_computations(Z, mu, S)
 
         #psi1
@@ -173,7 +182,9 @@ class RBF(Kern):
 
         return grad
 
-    def gradients_muS_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
+    def gradients_q_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, Z, posterior_variational):
+        mu = posterior_variational.mean
+        S = posterior_variational.variance
         self._psi_computations(Z, mu, S)
         #psi1
         tmp = self._psi1[:, :, None] / self.lengthscale2 / self._psi1_denom
diff --git a/GPy/kern/_src/ss_rbf.py b/GPy/kern/_src/ss_rbf.py
deleted file mode 100644
index cab8fd11..00000000
--- a/GPy/kern/_src/ss_rbf.py
+++ /dev/null
@@ -1,352 +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 kernpart import Kernpart
-from ...util.linalg import tdot
-from ...util.misc import fast_array_equal, param_to_array
-from ...core.parameterization import Param
-
-class SS_RBF(Kernpart):
-    """
-    The RBF kernel for Spike-and-Slab GPLVM
-    Radial Basis Function kernel, aka squared-exponential, exponentiated quadratic or Gaussian kernel:
-
-    .. math::
-
-       k(r) = \sigma^2 \exp \\bigg(- \\frac{1}{2} r^2 \\bigg) \ \ \ \ \  \\text{ where  } r^2 = \sum_{i=1}^d \\frac{ (x_i-x^\prime_i)^2}{\ell_i^2}
-
-    where \ell_i is the lengthscale, \sigma^2 the variance and d the dimensionality of the input.
-
-    :param input_dim: the number of input dimensions
-    :type input_dim: int
-    :param variance: the variance of the kernel
-    :type variance: float
-    :param lengthscale: the vector of lengthscale of the kernel
-    :type lengthscale: array or list of the appropriate size (or float if there is only one lengthscale parameter)
-    :rtype: kernel object
-    """
-
-    def __init__(self, input_dim, variance=1., lengthscale=None, name='rbf'):
-        super(RBF, self).__init__(input_dim, name)
-        self.input_dim = input_dim
-
-        if lengthscale is not None:
-            lengthscale = np.asarray(lengthscale)
-            assert lengthscale.size == self.input_dim, "bad number of lengthscales"
-        else:
-            lengthscale = np.ones(self.input_dim)
-
-        self.variance = Param('variance', variance)
-        self.lengthscale = Param('lengthscale', lengthscale)
-        self.lengthscale.add_observer(self, self.update_lengthscale)
-        self.add_parameters(self.variance, self.lengthscale)
-        self.parameters_changed() # initializes cache
-
-    def on_input_change(self, X):
-        #self._K_computations(X, None)
-        pass
-
-    def update_lengthscale(self, l):
-        self.lengthscale2 = np.square(self.lengthscale)
-
-    def parameters_changed(self):
-        # reset cached results
-        self._X, self._X2 = np.empty(shape=(2, 1))
-        self._Z, self._mu, self._S = np.empty(shape=(3, 1)) # cached versions of Z,mu,S
-
-    def K(self, X, X2, target):
-        self._K_computations(X, X2)
-        target += self.variance * self._K_dvar
-
-    def Kdiag(self, X, target):
-        np.add(target, self.variance, target)
-
-    def psi0(self, Z, mu, S, target):
-        target += self.variance
-
-    def psi1(self, Z, mu, S, target):
-        self._psi_computations(Z, mu, S)
-        target += self._psi1
-
-    def psi2(self, Z, mu, S, target):
-        self._psi_computations(Z, mu, S)
-        target += self._psi2
-
-    def update_gradients_full(self, dL_dK, X):
-        self._K_computations(X, None)
-        self.variance.gradient = np.sum(self._K_dvar * dL_dK)
-        if self.ARD:
-            self.lengthscale.gradient = self._dL_dlengthscales_via_K(dL_dK, X, None)
-        else:
-            self.lengthscale.gradient = (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dK)
-
-    def update_gradients_sparse(self, dL_dKmm, dL_dKnm, dL_dKdiag, X, Z):
-        #contributions from Kdiag
-        self.variance.gradient = np.sum(dL_dKdiag)
-
-        #from Knm
-        self._K_computations(X, Z)
-        self.variance.gradient += np.sum(dL_dKnm * self._K_dvar)
-        if self.ARD:
-            self.lengthscales.gradient = self._dL_dlengthscales_via_K(dL_dKnm, X, Z)
-
-        else:
-            self.lengthscale.gradient = (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dKmm)
-
-        #from Kmm
-        self._K_computations(Z, None)
-        self.variance.gradient += np.sum(dL_dKmm * self._K_dvar)
-        if self.ARD:
-            self.lengthscales.gradient += self._dL_dlengthscales_via_K(dL_dKmm, Z, None)
-        else:
-            self.lengthscale.gradient += (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dKmm)
-
-    def update_gradients_variational(self, dL_dKmm, dL_dpsi0, dL_dpsi1, dL_dpsi2, mu, S, Z):
-        self._psi_computations(Z, mu, S)
-
-        #contributions from psi0:
-        self.variance.gradient = np.sum(dL_dpsi0)
-
-        #from psi1
-        self.variance.gradient += np.sum(dL_dpsi1 * self._psi1 / self.variance)
-        d_length = self._psi1[:,:,None] * ((self._psi1_dist_sq - 1.)/(self.lengthscale*self._psi1_denom) +1./self.lengthscale)
-        dpsi1_dlength = d_length * dL_dpsi1[:, :, None]
-        if not self.ARD:
-            self.lengthscale.gradeint = dpsi1_dlength.sum()
-        else:
-            self.lengthscale.gradient = dpsi1_dlength.sum(0).sum(0)
-
-        #from psi2
-        d_var = 2.*self._psi2 / self.variance
-        d_length = 2.*self._psi2[:, :, :, None] * (self._psi2_Zdist_sq * self._psi2_denom + self._psi2_mudist_sq + S[:, None, None, :] / self.lengthscale2) / (self.lengthscale * self._psi2_denom)
-
-        self.variance.gradient += np.sum(dL_dpsi2 * d_var)
-        dpsi2_dlength = d_length * dL_dpsi2[:, :, :, None]
-        if not self.ARD:
-            self.lengthscale.gradient += dpsi2_dlength.sum()
-        else:
-            self.lengthscale.gradient += dpsi2_dlength.sum(0).sum(0).sum(0)
-
-        #from Kmm
-        self._K_computations(Z, None)
-        self.variance.gradient += np.sum(dL_dKmm * self._K_dvar)
-        if self.ARD:
-            self.lengthscales.gradient += self._dL_dlengthscales_via_K(dL_dKmm, Z, None)
-        else:
-            self.lengthscale.gradient += (self.variance / self.lengthscale) * np.sum(self._K_dvar * self._K_dist2 * dL_dK)
-
-    def gradients_X(self, dL_dK, X, X2, target):
-        #if self._X is None or X.base is not self._X.base or X2 is not None:
-        self._K_computations(X, X2)
-        if X2 is None:
-            _K_dist = 2*(X[:, None, :] - X[None, :, :])
-        else:
-            _K_dist = X[:, None, :] - X2[None, :, :] # don't cache this in _K_computations because it is high memory. If this function is being called, chances are we're not in the high memory arena.
-        gradients_X = (-self.variance / self.lengthscale2) * np.transpose(self._K_dvar[:, :, np.newaxis] * _K_dist, (1, 0, 2))
-        target += np.sum(gradients_X * dL_dK.T[:, :, None], 0)
-
-    def dKdiag_dX(self, dL_dKdiag, X, target):
-        pass
-
-    #---------------------------------------#
-    #             PSI statistics            #
-    #---------------------------------------#
-
-    def dpsi0_dmuS(self, dL_dpsi0, Z, mu, S, target_mu, target_S):
-        pass
-
-    def dpsi1_dZ(self, dL_dpsi1, Z, mu, S, target):
-        self._psi_computations(Z, mu, S)
-        denominator = (self.lengthscale2 * (self._psi1_denom))
-        dpsi1_dZ = -self._psi1[:, :, None] * ((self._psi1_dist / denominator))
-        target += np.sum(dL_dpsi1[:, :, None] * dpsi1_dZ, 0)
-
-    def dpsi1_dmuS(self, dL_dpsi1, Z, mu, S, target_mu, target_S):
-        self._psi_computations(Z, mu, S)
-        tmp = self._psi1[:, :, None] / self.lengthscale2 / self._psi1_denom
-        target_mu += np.sum(dL_dpsi1[:, :, None] * tmp * self._psi1_dist, 1)
-        target_S += np.sum(dL_dpsi1[:, :, None] * 0.5 * tmp * (self._psi1_dist_sq - 1), 1)
-
-    def dpsi2_dZ(self, dL_dpsi2, Z, mu, S, target):
-        self._psi_computations(Z, mu, S)
-        term1 = self._psi2_Zdist / self.lengthscale2 # num_inducing, num_inducing, input_dim
-        term2 = self._psi2_mudist / self._psi2_denom / self.lengthscale2 # N, num_inducing, num_inducing, input_dim
-        dZ = self._psi2[:, :, :, None] * (term1[None] + term2)
-        target += (dL_dpsi2[:, :, :, None] * dZ).sum(0).sum(0)
-
-    def dpsi2_dmuS(self, dL_dpsi2, Z, mu, S, target_mu, target_S):
-        """Think N,num_inducing,num_inducing,input_dim """
-        self._psi_computations(Z, mu, S)
-        tmp = self._psi2[:, :, :, None] / self.lengthscale2 / self._psi2_denom
-        target_mu += -2.*(dL_dpsi2[:, :, :, None] * tmp * self._psi2_mudist).sum(1).sum(1)
-        target_S += (dL_dpsi2[:, :, :, None] * tmp * (2.*self._psi2_mudist_sq - 1)).sum(1).sum(1)
-
-    #---------------------------------------#
-    #            Precomputations            #
-    #---------------------------------------#
-
-    def _K_computations(self, X, X2):
-        #params = self._get_params()
-        if not (fast_array_equal(X, self._X) and fast_array_equal(X2, self._X2)):# and fast_array_equal(self._params_save , params)):
-            #self._X = X.copy()
-            #self._params_save = params.copy()
-            if X2 is None:
-                self._X2 = None
-                X = X / self.lengthscale
-                Xsquare = np.sum(np.square(X), 1)
-                self._K_dist2 = -2.*tdot(X) + (Xsquare[:, None] + Xsquare[None, :])
-            else:
-                self._X2 = X2.copy()
-                X = X / self.lengthscale
-                X2 = X2 / self.lengthscale
-                self._K_dist2 = -2.*np.dot(X, X2.T) + (np.sum(np.square(X), 1)[:, None] + np.sum(np.square(X2), 1)[None, :])
-            self._K_dvar = np.exp(-0.5 * self._K_dist2)
-
-    def _dL_dlengthscales_via_K(self, dL_dK, X, X2):
-        """
-        A helper function for update_gradients_* methods
-
-        Computes the derivative of the objective L wrt the lengthscales via
-
-        dL_dl = sum_{i,j}(dL_dK_{ij} dK_dl)
-
-        assumes self._K_computations has just been called.
-
-        This is only valid if self.ARD=True
-        """
-        target = np.zeros(self.input_dim)
-        dvardLdK = self._K_dvar * dL_dK
-        var_len3 = self.variance / np.power(self.lengthscale, 3)
-        if X2 is None:
-            # save computation for the symmetrical case
-            dvardLdK = dvardLdK + dvardLdK.T
-            code = """
-            int q,i,j;
-            double tmp;
-            for(q=0; q<input_dim; q++){
-              tmp = 0;
-              for(i=0; i<num_data; i++){
-                for(j=0; j<i; j++){
-                  tmp += (X(i,q)-X(j,q))*(X(i,q)-X(j,q))*dvardLdK(i,j);
-                }
-              }
-              target(q) += var_len3(q)*tmp;
-            }
-            """
-            num_data, num_inducing, input_dim = X.shape[0], X.shape[0], self.input_dim
-            X, dvardLdK = param_to_array(X, dvardLdK)
-            weave.inline(code, arg_names=['num_data', 'num_inducing', 'input_dim', 'X', 'target', 'dvardLdK', 'var_len3'], type_converters=weave.converters.blitz, **self.weave_options)
-        else:
-            code = """
-            int q,i,j;
-            double tmp;
-            for(q=0; q<input_dim; q++){
-              tmp = 0;
-              for(i=0; i<num_data; i++){
-                for(j=0; j<num_inducing; j++){
-                  tmp += (X(i,q)-X2(j,q))*(X(i,q)-X2(j,q))*dvardLdK(i,j);
-                }
-              }
-              target(q) += var_len3(q)*tmp;
-            }
-            """
-            num_data, num_inducing, input_dim = X.shape[0], X2.shape[0], self.input_dim
-            X, X2, dvardLdK = param_to_array(X, X2, dvardLdK)
-            weave.inline(code, arg_names=['num_data', 'num_inducing', 'input_dim', 'X', 'X2', 'target', 'dvardLdK', 'var_len3'], type_converters=weave.converters.blitz, **self.weave_options)
-        return target
-
-
-
-    def _psi_computations(self, Z, mu, S):
-        # here are the "statistics" for psi1 and psi2
-        Z_changed = not fast_array_equal(Z, self._Z)
-        if Z_changed:
-            # Z has changed, compute Z specific stuff
-            self._psi2_Zhat = 0.5 * (Z[:, None, :] + Z[None, :, :]) # M,M,Q
-            self._psi2_Zdist = 0.5 * (Z[:, None, :] - Z[None, :, :]) # M,M,Q
-            self._psi2_Zdist_sq = np.square(self._psi2_Zdist / self.lengthscale) # M,M,Q
-
-        if Z_changed or not fast_array_equal(mu, self._mu) or not fast_array_equal(S, self._S):
-            # something's changed. recompute EVERYTHING
-
-            # psi1
-            self._psi1_denom = S[:, None, :] / self.lengthscale2 + 1.
-            self._psi1_dist = Z[None, :, :] - mu[:, None, :]
-            self._psi1_dist_sq = np.square(self._psi1_dist) / self.lengthscale2 / self._psi1_denom
-            self._psi1_exponent = -0.5 * np.sum(self._psi1_dist_sq + np.log(self._psi1_denom), -1)
-            self._psi1 = self.variance * np.exp(self._psi1_exponent)
-
-            # psi2
-            self._psi2_denom = 2.*S[:, None, None, :] / self.lengthscale2 + 1. # N,M,M,Q
-            self._psi2_mudist, self._psi2_mudist_sq, self._psi2_exponent, _ = self.weave_psi2(mu, self._psi2_Zhat)
-            # self._psi2_mudist = mu[:,None,None,:]-self._psi2_Zhat #N,M,M,Q
-            # self._psi2_mudist_sq = np.square(self._psi2_mudist)/(self.lengthscale2*self._psi2_denom)
-            # self._psi2_exponent = np.sum(-self._psi2_Zdist_sq -self._psi2_mudist_sq -0.5*np.log(self._psi2_denom),-1) #N,M,M,Q
-            self._psi2 = np.square(self.variance) * np.exp(self._psi2_exponent) # N,M,M,Q
-
-            # store matrices for caching
-            self._Z, self._mu, self._S = Z, mu, S
-
-    def weave_psi2(self, mu, Zhat):
-        N, input_dim = mu.shape
-        num_inducing = Zhat.shape[0]
-
-        mudist = np.empty((N, num_inducing, num_inducing, input_dim))
-        mudist_sq = np.empty((N, num_inducing, num_inducing, input_dim))
-        psi2_exponent = np.zeros((N, num_inducing, num_inducing))
-        psi2 = np.empty((N, num_inducing, num_inducing))
-
-        psi2_Zdist_sq = self._psi2_Zdist_sq
-        _psi2_denom = self._psi2_denom.squeeze().reshape(N, self.input_dim)
-        half_log_psi2_denom = 0.5 * np.log(self._psi2_denom).squeeze().reshape(N, self.input_dim)
-        variance_sq = float(np.square(self.variance))
-        if self.ARD:
-            lengthscale2 = self.lengthscale2
-        else:
-            lengthscale2 = np.ones(input_dim) * self.lengthscale2
-        code = """
-        double tmp;
-
-        #pragma omp parallel for private(tmp)
-        for (int n=0; n<N; n++){
-            for (int m=0; m<num_inducing; m++){
-               for (int mm=0; mm<(m+1); mm++){
-                   for (int q=0; q<input_dim; q++){
-                       //compute mudist
-                       tmp = mu(n,q) - Zhat(m,mm,q);
-                       mudist(n,m,mm,q) = tmp;
-                       mudist(n,mm,m,q) = tmp;
-
-                       //now mudist_sq
-                       tmp = tmp*tmp/lengthscale2(q)/_psi2_denom(n,q);
-                       mudist_sq(n,m,mm,q) = tmp;
-                       mudist_sq(n,mm,m,q) = tmp;
-
-                       //now psi2_exponent
-                       tmp = -psi2_Zdist_sq(m,mm,q) - tmp - half_log_psi2_denom(n,q);
-                       psi2_exponent(n,mm,m) += tmp;
-                       if (m !=mm){
-                           psi2_exponent(n,m,mm) += tmp;
-                       }
-                   //psi2 would be computed like this, but np is faster
-                   //tmp = variance_sq*exp(psi2_exponent(n,m,mm));
-                   //psi2(n,m,mm) = tmp;
-                   //psi2(n,mm,m) = tmp;
-                   }
-                }
-            }
-        }
-
-        """
-
-        support_code = """
-        #include <omp.h>
-        #include <math.h>
-        """
-        weave.inline(code, support_code=support_code, libraries=['gomp'],
-                     arg_names=['N', 'num_inducing', 'input_dim', 'mu', 'Zhat', 'mudist_sq', 'mudist', 'lengthscale2', '_psi2_denom', 'psi2_Zdist_sq', 'psi2_exponent', 'half_log_psi2_denom', 'psi2', 'variance_sq'],
-                     type_converters=weave.converters.blitz, **self.weave_options)
-
-        return mudist, mudist_sq, psi2_exponent, psi2
diff --git a/GPy/models/bayesian_gplvm.py b/GPy/models/bayesian_gplvm.py
index 8aa378ce..cc68de68 100644
--- a/GPy/models/bayesian_gplvm.py
+++ b/GPy/models/bayesian_gplvm.py
@@ -66,7 +66,7 @@ class BayesianGPLVM(SparseGP, GPLVM):
         super(BayesianGPLVM, self).parameters_changed()
 
         self._log_marginal_likelihood -= self.KL_divergence()
-        dL_dmu, dL_dS = self.kern.gradients_muS_variational(mu=self.X, S=self.X_variance, Z=self.Z, **self.grad_dict)
+        dL_dmu, dL_dS = self.kern.gradients_q_variational(posterior_variational=self.q, Z=self.Z, **self.grad_dict)
 
         # dL:
         self.q.mean.gradient  = dL_dmu
diff --git a/GPy/plotting/matplot_dep/dim_reduction_plots.py b/GPy/plotting/matplot_dep/dim_reduction_plots.py
index 74292c05..3f4ea9b0 100644
--- a/GPy/plotting/matplot_dep/dim_reduction_plots.py
+++ b/GPy/plotting/matplot_dep/dim_reduction_plots.py
@@ -1,8 +1,8 @@
 import pylab as pb
 import numpy as np
-from ... import util
 from latent_space_visualizations.controllers.imshow_controller import ImshowController,ImAnnotateController
-from GPy.util.misc import param_to_array
+from ...util.misc import param_to_array
+from .base_plots import x_frame2D
 import itertools
 import Tango
 from matplotlib.cm import get_cmap
@@ -37,7 +37,7 @@ def plot_latent(model, labels=None, which_indices=None,
     if ax is None:
         fig = pb.figure(num=fignum)
         ax = fig.add_subplot(111)
-    util.plot.Tango.reset()
+    Tango.reset()
 
     if labels is None:
         labels = np.ones(model.num_data)
@@ -46,7 +46,7 @@ def plot_latent(model, labels=None, which_indices=None,
     X = param_to_array(model.X)
 
     # first, plot the output variance as a function of the latent space
-    Xtest, xx, yy, xmin, xmax = util.plot.x_frame2D(X[:, [input_1, input_2]], resolution=resolution)
+    Xtest, xx, yy, xmin, xmax = x_frame2D(X[:, [input_1, input_2]], resolution=resolution)
     Xtest_full = np.zeros((Xtest.shape[0], model.X.shape[1]))
 
     def plot_function(x):
@@ -87,7 +87,7 @@ def plot_latent(model, labels=None, which_indices=None,
         else:
             x = X[index, input_1]
             y = X[index, input_2]
-        ax.scatter(x, y, marker=m, s=s, color=util.plot.Tango.nextMedium(), label=this_label)
+        ax.scatter(x, y, marker=m, s=s, color=Tango.nextMedium(), label=this_label)
 
     ax.set_xlabel('latent dimension %i' % input_1)
     ax.set_ylabel('latent dimension %i' % input_2)
@@ -120,7 +120,7 @@ def plot_magnification(model, labels=None, which_indices=None,
     if ax is None:
         fig = pb.figure(num=fignum)
         ax = fig.add_subplot(111)
-    util.plot.Tango.reset()
+    Tango.reset()
 
     if labels is None:
         labels = np.ones(model.num_data)
@@ -128,7 +128,7 @@ def plot_magnification(model, labels=None, which_indices=None,
     input_1, input_2 = most_significant_input_dimensions(model, which_indices)
 
     # first, plot the output variance as a function of the latent space
-    Xtest, xx, yy, xmin, xmax = util.plot.x_frame2D(model.X[:, [input_1, input_2]], resolution=resolution)
+    Xtest, xx, yy, xmin, xmax = x_frame2D(model.X[:, [input_1, input_2]], resolution=resolution)
     Xtest_full = np.zeros((Xtest.shape[0], model.X.shape[1]))
 
     def plot_function(x):
@@ -165,7 +165,7 @@ def plot_magnification(model, labels=None, which_indices=None,
         else:
             x = model.X[index, input_1]
             y = model.X[index, input_2]
-        ax.scatter(x, y, marker=m, s=s, color=util.plot.Tango.nextMedium(), label=this_label)
+        ax.scatter(x, y, marker=m, s=s, color=Tango.nextMedium(), label=this_label)
 
     ax.set_xlabel('latent dimension %i' % input_1)
     ax.set_ylabel('latent dimension %i' % input_2)
@@ -205,7 +205,7 @@ def plot_steepest_gradient_map(model, fignum=None, ax=None, which_indices=None,
         return dmu_dX[indices, argmax], np.array(labels)[argmax]
 
     if ax is None:
-        fig = pyplot.figure(num=fignum)
+        fig = pb.figure(num=fignum)
         ax = fig.add_subplot(111)
 
     if data_labels is None:
@@ -241,7 +241,7 @@ def plot_steepest_gradient_map(model, fignum=None, ax=None, which_indices=None,
     ax.legend()
     ax.figure.tight_layout()
     if updates:
-        pyplot.show()
+        pb.show()
         clear = raw_input('Enter to continue')
         if clear.lower() in 'yes' or clear == '':
             controller.deactivate()
diff --git a/GPy/plotting/matplot_dep/kernel_plots.py b/GPy/plotting/matplot_dep/kernel_plots.py
index 30157294..3436c4ff 100644
--- a/GPy/plotting/matplot_dep/kernel_plots.py
+++ b/GPy/plotting/matplot_dep/kernel_plots.py
@@ -1,7 +1,6 @@
 # Copyright (c) 2012, GPy authors (see AUTHORS.txt).
 # Licensed under the BSD 3-clause license (see LICENSE.txt)
 
-import sys
 import numpy as np
 import pylab as pb
 import Tango
@@ -29,22 +28,23 @@ def plot_ARD(kernel, fignum=None, ax=None, title='', legend=False):
     xticklabels = []
     bars = []
     x0 = 0
-    for p in kernel._parameters_:
-        c = Tango.nextMedium()
-        if hasattr(p, 'ARD') and p.ARD:
-            if title is None:
-                ax.set_title('ARD parameters, %s kernel' % p.name)
-            else:
-                ax.set_title(title)
-            if isinstance(p, Linear):
-                ard_params = p.variances
-            else:
-                ard_params = 1. / p.lengthscale
-
-            x = np.arange(x0, x0 + len(ard_params))
-            bars.append(ax.bar(x, ard_params, align='center', color=c, edgecolor='k', linewidth=1.2, label=p.name.replace("_"," ")))
-            xticklabels.extend([r"$\mathrm{{{name}}}\ {x}$".format(name=p.name, x=i) for i in np.arange(len(ard_params))])
-            x0 += len(ard_params)
+    #for p in kernel._parameters_:
+    p = kernel
+    c = Tango.nextMedium()
+    if hasattr(p, 'ARD') and p.ARD:
+        if title is None:
+            ax.set_title('ARD parameters, %s kernel' % p.name)
+        else:
+            ax.set_title(title)
+        if isinstance(p, Linear):
+            ard_params = p.variances
+        else:
+            ard_params = 1. / p.lengthscale
+        x = np.arange(x0, x0 + len(ard_params))
+        from ...util.misc import param_to_array
+        bars.append(ax.bar(x, param_to_array(ard_params), align='center', color=c, edgecolor='k', linewidth=1.2, label=p.name.replace("_"," ")))
+        xticklabels.extend([r"$\mathrm{{{name}}}\ {x}$".format(name=p.name, x=i) for i in np.arange(len(ard_params))])
+        x0 += len(ard_params)
     x = np.arange(x0)
     transOffset = offset_copy(ax.transData, fig=fig,
                               x=0., y= -2., units='points')
diff --git a/GPy/plotting/matplot_dep/models_plots.py b/GPy/plotting/matplot_dep/models_plots.py
index 47c8642e..59c32775 100644
--- a/GPy/plotting/matplot_dep/models_plots.py
+++ b/GPy/plotting/matplot_dep/models_plots.py
@@ -56,7 +56,10 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
     if ax is None:
         fig = pb.figure(num=fignum)
         ax = fig.add_subplot(111)
-
+    
+    X, Y = param_to_array(model.X, model.Y)
+    if model.has_uncertain_inputs(): X_variance = model.X_variance
+    
     #work out what the inputs are for plotting (1D or 2D)
     fixed_dims = np.array([i for i,v in fixed_inputs])
     free_dims = np.setdiff1d(np.arange(model.input_dim),fixed_dims)
@@ -66,7 +69,7 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
 
         #define the frame on which to plot
         resolution = resolution or 200
-        Xnew, xmin, xmax = x_frame1D(model.X[:,free_dims], plot_limits=plot_limits)
+        Xnew, xmin, xmax = x_frame1D(X[:,free_dims], plot_limits=plot_limits)
         Xgrid = np.empty((Xnew.shape[0],model.input_dim))
         Xgrid[:,free_dims] = Xnew
         for i,v in fixed_inputs:
@@ -77,13 +80,13 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
             m, v = model._raw_predict(Xgrid)
             lower = m - 2*np.sqrt(v)
             upper = m + 2*np.sqrt(v)
-            Y = model.Y
+            Y = Y
         else:
             m, v, lower, upper = model.predict(Xgrid)
-            Y = model.Y
+            Y = Y
         for d in which_data_ycols:
             gpplot(Xnew, m[:, d], lower[:, d], upper[:, d], axes=ax, edgecol=linecol, fillcol=fillcol)
-            ax.plot(model.X[which_data_rows,free_dims], Y[which_data_rows, d], 'kx', mew=1.5)
+            ax.plot(X[which_data_rows,free_dims], Y[which_data_rows, d], 'kx', mew=1.5)
 
         #optionally plot some samples
         if samples: #NOTE not tested with fixed_inputs
@@ -95,8 +98,8 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
         
         #add error bars for uncertain (if input uncertainty is being modelled)
         if hasattr(model,"has_uncertain_inputs") and model.has_uncertain_inputs():
-            ax.errorbar(model.X[which_data_rows, free_dims], model.Y[which_data_rows, which_data_ycols],
-                        xerr=2 * np.sqrt(model.X_variance[which_data_rows, free_dims]),
+            ax.errorbar(X[which_data_rows, free_dims].flatten(), Y[which_data_rows, which_data_ycols].flatten(),
+                        xerr=2 * np.sqrt(X_variance[which_data_rows, free_dims].flatten()),
                         ecolor='k', fmt=None, elinewidth=.5, alpha=.5)
 
 
@@ -120,7 +123,7 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
 
         #define the frame for plotting on
         resolution = resolution or 50
-        Xnew, _, _, xmin, xmax = x_frame2D(model.X[:,free_dims], plot_limits, resolution)
+        Xnew, _, _, xmin, xmax = x_frame2D(X[:,free_dims], plot_limits, resolution)
         Xgrid = np.empty((Xnew.shape[0],model.input_dim))
         Xgrid[:,free_dims] = Xnew
         for i,v in fixed_inputs:
@@ -130,14 +133,14 @@ def plot_fit(model, plot_limits=None, which_data_rows='all',
         #predict on the frame and plot
         if plot_raw:
             m, _ = model._raw_predict(Xgrid)
-            Y = model.Y
+            Y = Y
         else:
             m, _, _, _ = model.predict(Xgrid)
             Y = model.data
         for d in which_data_ycols:
             m_d = m[:,d].reshape(resolution, resolution).T
             ax.contour(x, y, m_d, levels, vmin=m.min(), vmax=m.max(), cmap=pb.cm.jet)
-            ax.scatter(model.X[which_data_rows, free_dims[0]], model.X[which_data_rows, free_dims[1]], 40, Y[which_data_rows, d], cmap=pb.cm.jet, vmin=m.min(), vmax=m.max(), linewidth=0.)
+            ax.scatter(X[which_data_rows, free_dims[0]], X[which_data_rows, free_dims[1]], 40, Y[which_data_rows, d], cmap=pb.cm.jet, vmin=m.min(), vmax=m.max(), linewidth=0.)
 
         #set the limits of the plot to some sensible values
         ax.set_xlim(xmin[0], xmax[0])
diff --git a/GPy/testing/index_operations_tests.py b/GPy/testing/index_operations_tests.py
index d5ef7007..171db5cc 100644
--- a/GPy/testing/index_operations_tests.py
+++ b/GPy/testing/index_operations_tests.py
@@ -24,6 +24,13 @@ class Test(unittest.TestCase):
         self.param_index.remove(one, [1])
         self.assertListEqual(self.param_index[one].tolist(), [3])        
 
+    def test_shift_left(self):
+        self.param_index.shift_left(1, 2)
+        self.assertListEqual(self.param_index[three].tolist(), [2,5])
+        self.assertListEqual(self.param_index[two].tolist(), [0,3])
+        self.assertListEqual(self.param_index[one].tolist(), [1])        
+
+
     def test_index_view(self):
         #=======================================================================
         #          0    1    2    3    4    5    6    7    8    9
diff --git a/GPy/testing/parameterized_tests.py b/GPy/testing/parameterized_tests.py
index ff57606a..6f13d294 100644
--- a/GPy/testing/parameterized_tests.py
+++ b/GPy/testing/parameterized_tests.py
@@ -10,8 +10,8 @@ import numpy as np
 class Test(unittest.TestCase):
 
     def setUp(self):
-        self.rbf = GPy.kern.rbf(1)
-        self.white = GPy.kern.white(1)
+        self.rbf = GPy.kern.RBF(1)
+        self.white = GPy.kern.White(1)
         from GPy.core.parameterization import Param
         from GPy.core.parameterization.transformations import Logistic
         self.param = Param('param', np.random.rand(25,2), Logistic(0, 1))
@@ -39,14 +39,13 @@ class Test(unittest.TestCase):
         
         
     def test_remove_parameter(self):
-        from GPy.core.parameterization.transformations import FIXED, UNFIXED, __fixed__
+        from GPy.core.parameterization.transformations import FIXED, UNFIXED, __fixed__, Logexp
         self.white.fix()
         self.test1.remove_parameter(self.white)
         self.assertIs(self.test1._fixes_,None)
         
         self.assertListEqual(self.white._fixes_.tolist(), [FIXED])
-        self.assertIs(self.white.constraints,self.white.white.constraints._param_index_ops)
-        self.assertEquals(self.white.white.constraints._offset, 0)
+        self.assertEquals(self.white.constraints._offset, 0)
         self.assertIs(self.test1.constraints, self.rbf.constraints._param_index_ops)
         self.assertIs(self.test1.constraints, self.param.constraints._param_index_ops)        
         
@@ -57,18 +56,19 @@ class Test(unittest.TestCase):
         self.assertListEqual(self.test1.constraints[__fixed__].tolist(), [0])
         self.assertIs(self.white._fixes_,None)
         self.assertListEqual(self.test1._fixes_.tolist(),[FIXED] + [UNFIXED] * 52)
+        
         self.test1.remove_parameter(self.white)
         self.assertIs(self.test1._fixes_,None)
         self.assertListEqual(self.white._fixes_.tolist(), [FIXED])
-        self.assertIs(self.white.constraints,self.white.white.constraints._param_index_ops)
         self.assertIs(self.test1.constraints, self.rbf.constraints._param_index_ops)
-        self.assertIs(self.test1.constraints, self.param.constraints._param_index_ops)        
+        self.assertIs(self.test1.constraints, self.param.constraints._param_index_ops)
+        self.assertListEqual(self.test1.constraints[Logexp()].tolist(), [0,1])
         
     def test_add_parameter_already_in_hirarchy(self):
         self.test1.add_parameter(self.white._parameters_[0])
         
     def test_default_constraints(self):
-        self.assertIs(self.rbf.rbf.variance.constraints._param_index_ops, self.rbf.constraints._param_index_ops)
+        self.assertIs(self.rbf.variance.constraints._param_index_ops, self.rbf.constraints._param_index_ops)
         self.assertIs(self.test1.constraints, self.rbf.constraints._param_index_ops)
         self.assertListEqual(self.rbf.constraints.indices()[0].tolist(), range(2))
         from GPy.core.parameterization.transformations import Logexp