diff --git a/GPy/core/sparse_gp_mpi.py b/GPy/core/sparse_gp_mpi.py
index d747ac83..3c3d5398 100644
--- a/GPy/core/sparse_gp_mpi.py
+++ b/GPy/core/sparse_gp_mpi.py
@@ -38,7 +38,7 @@ class SparseGP_MPI(SparseGP):
                  mean_function=None, inference_method=None, name='sparse gp',
                  Y_metadata=None, mpi_comm=None, normalizer=False):
         self._IN_OPTIMIZATION_ = False
-        if mpi_comm != None:
+        if mpi_comm is not None:
             if inference_method is None:
                 inference_method = VarDTC_minibatch(mpi_comm=mpi_comm)
             else:
@@ -52,7 +52,7 @@ class SparseGP_MPI(SparseGP):
 
         self.mpi_comm = mpi_comm
         # Manage the data (Y) division
-        if mpi_comm != None:
+        if mpi_comm is not None:
             from ..util.parallel import divide_data
             N_start, N_end, N_list = divide_data(Y.shape[0], mpi_comm.rank, mpi_comm.size)
             self.N_range = (N_start, N_end)
@@ -65,7 +65,7 @@ class SparseGP_MPI(SparseGP):
     def __getstate__(self):
         dc = super(SparseGP_MPI, self).__getstate__()
         dc['mpi_comm'] = None
-        if self.mpi_comm != None:
+        if self.mpi_comm is not None:
             del dc['N_range']
             del dc['N_list']
             del dc['Y_local']
@@ -81,7 +81,7 @@ class SparseGP_MPI(SparseGP):
 
     @SparseGP.optimizer_array.setter
     def optimizer_array(self, p):
-        if self.mpi_comm != None:
+        if self.mpi_comm is not None:
             if self._IN_OPTIMIZATION_ and self.mpi_comm.rank==0:
                 self.mpi_comm.Bcast(np.int32(1),root=0)
             self.mpi_comm.Bcast(p, root=0)
diff --git a/GPy/inference/latent_function_inference/var_dtc_parallel.py b/GPy/inference/latent_function_inference/var_dtc_parallel.py
index 603623a7..63624ca9 100644
--- a/GPy/inference/latent_function_inference/var_dtc_parallel.py
+++ b/GPy/inference/latent_function_inference/var_dtc_parallel.py
@@ -118,7 +118,7 @@ class VarDTC_minibatch(LatentFunctionInference):
         if not het_noise:
             YRY_full = trYYT*beta
 
-        if self.mpi_comm != None:
+        if self.mpi_comm is not None:
             from mpi4py import MPI
             psi0_all = np.array(psi0_full)
             psi1Y_all = psi1Y_full.copy()
@@ -142,7 +142,7 @@ class VarDTC_minibatch(LatentFunctionInference):
 
         num_data, output_dim = Y.shape
         input_dim = Z.shape[0]
-        if self.mpi_comm != None:
+        if self.mpi_comm is not None:
             from mpi4py import MPI
             num_data_all = np.array(num_data,dtype=np.int32)
             self.mpi_comm.Allreduce([np.int32(num_data), MPI.INT], [num_data_all, MPI.INT])
@@ -384,7 +384,7 @@ def update_gradients(model, mpi_comm=None):
                 dL_dthetaL += grad_dict['dL_dthetaL']
 
     # Gather the gradients from multiple MPI nodes
-    if mpi_comm != None:
+    if mpi_comm is not None:
         from mpi4py import MPI
         if het_noise:
             raise "het_noise not implemented!"
@@ -407,7 +407,7 @@ def update_gradients(model, mpi_comm=None):
     # update for the KL divergence
     model.variational_prior.update_gradients_KL(X)
 
-    if mpi_comm != None:
+    if mpi_comm is not None:
         from mpi4py import MPI
         KL_div_all = np.array(KL_div)
         mpi_comm.Allreduce([np.float64(KL_div), MPI.DOUBLE], [KL_div_all, MPI.DOUBLE])
@@ -467,7 +467,7 @@ def update_gradients_sparsegp(model, mpi_comm=None):
             dL_dthetaL += grad_dict['dL_dthetaL']
     
     # Gather the gradients from multiple MPI nodes
-    if mpi_comm != None:
+    if mpi_comm is not None:
         from mpi4py import MPI
         if het_noise:
             raise "het_noise not implemented!"
diff --git a/GPy/models/ss_mrd.py b/GPy/models/ss_mrd.py
index c4dbec78..bf06e4e0 100644
--- a/GPy/models/ss_mrd.py
+++ b/GPy/models/ss_mrd.py
@@ -183,7 +183,7 @@ class SSMRD(Model):
 
     @Model.optimizer_array.setter
     def optimizer_array(self, p):
-        if self.mpi_comm != None:
+        if self.mpi_comm is not None:
             if self._IN_OPTIMIZATION_ and self.mpi_comm.rank == 0:
                 self.mpi_comm.Bcast(np.int32(1), root=0)
             self.mpi_comm.Bcast(p, root=0)
diff --git a/GPy/plotting/matplot_dep/visualize.py b/GPy/plotting/matplot_dep/visualize.py
index a6c2f233..85462cde 100644
--- a/GPy/plotting/matplot_dep/visualize.py
+++ b/GPy/plotting/matplot_dep/visualize.py
@@ -167,7 +167,7 @@ class lvm(matplotlib_show):
 
     def show_sensitivities(self):
         # A click in the bar chart axis for selection a dimension.
-        if self.sense_axes != None:
+        if self.sense_axes is not None:
             self.sense_axes.cla()
             self.sense_axes.bar(np.arange(self.model.input_dim), self.model.input_sensitivity(), color='b')