diff --git a/GPy/inference/latent_function_inference/dtc.py b/GPy/inference/latent_function_inference/dtc.py
index 5590a079..57a451b2 100644
--- a/GPy/inference/latent_function_inference/dtc.py
+++ b/GPy/inference/latent_function_inference/dtc.py
@@ -29,7 +29,7 @@ class DTC(LatentFunctionInference):
         #make sure the noise is not hetero
         beta = 1./likelihood.gaussian_variance(Y_metadata)
         if beta.size > 1:
-            raise NotImplementedError, "no hetero noise with this implementation of DTC"
+            raise NotImplementedError("no hetero noise with this implementation of DTC")
 
         Kmm = kern.K(Z)
         Knn = kern.Kdiag(X)
@@ -97,7 +97,7 @@ class vDTC(object):
         #make sure the noise is not hetero
         beta = 1./likelihood.gaussian_variance(Y_metadata)
         if beta.size > 1:
-            raise NotImplementedError, "no hetero noise with this implementation of DTC"
+            raise NotImplementedError("no hetero noise with this implementation of DTC")
 
         Kmm = kern.K(Z)
         Knn = kern.Kdiag(X)
diff --git a/GPy/inference/latent_function_inference/expectation_propagation_dtc.py b/GPy/inference/latent_function_inference/expectation_propagation_dtc.py
index 0f972a84..e25df388 100644
--- a/GPy/inference/latent_function_inference/expectation_propagation_dtc.py
+++ b/GPy/inference/latent_function_inference/expectation_propagation_dtc.py
@@ -314,7 +314,7 @@ def _compute_dL_dR(likelihood, het_noise, uncertain_inputs, LB, _LBi_Lmi_psi1Vf,
         dL_dR = None
     elif het_noise:
         if uncertain_inputs:
-            raise NotImplementedError, "heteroscedatic derivates with uncertain inputs not implemented"
+            raise NotImplementedError("heteroscedatic derivates with uncertain inputs not implemented")
         else:
             #from ...util.linalg import chol_inv
             #LBi = chol_inv(LB)
diff --git a/GPy/inference/latent_function_inference/fitc.py b/GPy/inference/latent_function_inference/fitc.py
index a184c6c4..abe53f3d 100644
--- a/GPy/inference/latent_function_inference/fitc.py
+++ b/GPy/inference/latent_function_inference/fitc.py
@@ -26,7 +26,7 @@ class FITC(LatentFunctionInference):
         #make sure the noise is not hetero
         sigma_n = likelihood.gaussian_variance(Y_metadata)
         if sigma_n.size >1:
-            raise NotImplementedError, "no hetero noise with this implementation of FITC"
+            raise NotImplementedError("no hetero noise with this implementation of FITC")
 
         Kmm = kern.K(Z)
         Knn = kern.Kdiag(X)
diff --git a/GPy/inference/latent_function_inference/posterior.py b/GPy/inference/latent_function_inference/posterior.py
index 34f0b3bb..73d65df6 100644
--- a/GPy/inference/latent_function_inference/posterior.py
+++ b/GPy/inference/latent_function_inference/posterior.py
@@ -52,7 +52,7 @@ class Posterior(object):
                 or ((mean is not None) and (cov is not None)):
             pass # we have sufficient to compute the posterior
         else:
-            raise ValueError, "insufficient information to compute the posterior"
+            raise ValueError("insufficient information to compute the posterior")
 
         self._K_chol = K_chol
         self._K = K
@@ -134,13 +134,13 @@ class Posterior(object):
                 #self._woodbury_chol = jitchol(W)
             #try computing woodbury chol from cov
             elif self._covariance is not None:
-                raise NotImplementedError, "TODO: check code here"
+                raise NotImplementedError("TODO: check code here")
                 B = self._K - self._covariance
                 tmp, _ = dpotrs(self.K_chol, B)
                 self._woodbury_inv, _ = dpotrs(self.K_chol, tmp.T)
                 _, _, self._woodbury_chol, _ = pdinv(self._woodbury_inv)
             else:
-                raise ValueError, "insufficient information to compute posterior"
+                raise ValueError("insufficient information to compute posterior")
         return self._woodbury_chol
 
     @property
diff --git a/GPy/inference/latent_function_inference/var_dtc.py b/GPy/inference/latent_function_inference/var_dtc.py
index db59df14..1be2557b 100644
--- a/GPy/inference/latent_function_inference/var_dtc.py
+++ b/GPy/inference/latent_function_inference/var_dtc.py
@@ -213,7 +213,7 @@ def _compute_dL_dR(likelihood, het_noise, uncertain_inputs, LB, _LBi_Lmi_psi1Vf,
         dL_dR = None
     elif het_noise:
         if uncertain_inputs:
-            raise NotImplementedError, "heteroscedatic derivates with uncertain inputs not implemented"
+            raise NotImplementedError("heteroscedatic derivates with uncertain inputs not implemented")
         else:
             #from ...util.linalg import chol_inv
             #LBi = chol_inv(LB)
diff --git a/GPy/inference/optimization/optimization.py b/GPy/inference/optimization/optimization.py
index 0d6887e5..600de35d 100644
--- a/GPy/inference/optimization/optimization.py
+++ b/GPy/inference/optimization/optimization.py
@@ -54,7 +54,7 @@ class Optimizer():
         self.time = str(end - start)
 
     def opt(self, f_fp=None, f=None, fp=None):
-        raise NotImplementedError, "this needs to be implemented to use the optimizer class"
+        raise NotImplementedError("this needs to be implemented to use the optimizer class")
 
     def plot(self):
         """