diff --git a/GPy/examples/fitc_class_01.py b/GPy/examples/fitc_class_01.py
deleted file mode 100644
index 38c9da63..00000000
--- a/GPy/examples/fitc_class_01.py
+++ /dev/null
@@ -1,53 +0,0 @@
-import pylab as pb
-import numpy as np
-import GPy
-pb.ion()
-pb.close('all')
-
-"""
-Simple 1D classification example
-:param seed : seed value for data generation (default is 4).
-:type seed: int
-"""
-seed=10000
-
-#data = GPy.util.datasets.toy_linear_1d_classification(seed=seed)
-#X = data['X']
-#Y = data['Y'][:, 0:1]
-#Y[Y == -1] = 0
-
-
-
-X = np.vstack((np.random.uniform(0,10,(10,1)),np.random.uniform(7,17,(10,1)),np.random.uniform(15,25,(10,1))))
-Y = np.vstack((np.zeros((10,1)),np.ones((10,1)),np.zeros((10,1))))
-
-# Kernel object
-kernel = GPy.kern.rbf(1) + GPy.kern.white(1)
-
-# Likelihood object
-distribution = GPy.likelihoods.likelihood_functions.probit()
-likelihood = GPy.likelihoods.EP(Y,distribution)
-
-Z = np.random.uniform(X.min(),X.max(),(10,1))
-#Z = np.array([0,20])[:,None]
-print Z
-
-# Model definition
-m = GPy.models.generalized_FITC(X,likelihood=likelihood,kernel=kernel,Z=Z,normalize_X=False)
-m.set('len',2.)
-
-m.ensure_default_constraints()
-# Optimize
-#m.constrain_fixed('iip')
-m.update_likelihood_approximation()
-print m.checkgrad(verbose=1)
-# Parameters optimization:
-#m.optimize()
-m.pseudo_EM() #FIXME
-
-# Plot
-pb.subplot(211)
-m.plot_f()
-pb.subplot(212)
-m.plot()
-print(m)
diff --git a/GPy/examples/fitc_class_02.py b/GPy/examples/fitc_class_02.py
deleted file mode 100644
index 71e10081..00000000
--- a/GPy/examples/fitc_class_02.py
+++ /dev/null
@@ -1,67 +0,0 @@
-import pylab as pb
-import numpy as np
-import GPy
-pb.close('all')
-
-seed=10000
-"""Run a Gaussian process classification on the crescent data. The demonstration calls the basic GP classification model and uses EP to approximate the likelihood.
-
-:param model_type: type of model to fit ['Full', 'FITC', 'DTC'].
-:param seed : seed value for data generation.
-:type seed: int
-:param inducing : number of inducing variables (only used for 'FITC' or 'DTC').
-:type inducing: int
-"""
-
-data = GPy.util.datasets.crescent_data(seed=seed)
-
-# Kernel object
-kernel = GPy.kern.rbf(data['X'].shape[1]) + GPy.kern.white(data['X'].shape[1])
-
-# Likelihood object
-distribution = GPy.likelihoods.likelihood_functions.probit()
-likelihood = GPy.likelihoods.EP(data['Y'],distribution)
-
-sample = np.random.randint(0,data['X'].shape[0],10)
-Z = data['X'][sample,:]
-# create sparse GP EP model
-m = GPy.models.generalized_FITC(data['X'],likelihood=likelihood,kernel=kernel,Z=Z)
-m.ensure_default_constraints()
-m.set('len',10.)
-
-#m.update_likelihood_approximation()
-
-# optimize
-#m.optimize()
-m.pseudo_EM()
-print(m)
-
-# plot
-m.plot()
-fitc = m
-
-pb.figure()
-# Kernel object
-kernel = GPy.kern.rbf(data['X'].shape[1]) + GPy.kern.white(data['X'].shape[1])
-
-# Likelihood object
-distribution = GPy.likelihoods.likelihood_functions.probit()
-likelihood = GPy.likelihoods.EP(data['Y'],distribution)
-
-#sample = np.random.randint(0,data['X'].shape[0],10)
-#Z = data['X'][sample,:]
-# create sparse GP EP model
-m = GPy.models.sparse_GP(data['X'],likelihood=likelihood,kernel=kernel,Z=Z)
-m.ensure_default_constraints()
-m.set('len',10.)
-
-#m.update_likelihood_approximation()
-
-# optimize
-#m.optimize()
-m.pseudo_EM()
-print(m)
-
-# plot
-m.plot()
-variational = m
diff --git a/GPy/examples/fitc_regr_01.py b/GPy/examples/fitc_regr_01.py
deleted file mode 100644
index 815e31a7..00000000
--- a/GPy/examples/fitc_regr_01.py
+++ /dev/null
@@ -1,53 +0,0 @@
-import pylab as pb
-import numpy as np
-import GPy
-pb.ion()
-pb.close('all')
-
-N = 400
-M = 10
-# sample inputs and outputs
-X = np.random.uniform(-3.,3.,(N,1))
-Y = np.sin(X)+np.random.randn(N,1)*0.05
-
-"""Run a 1D example of a sparse GP regression."""
-"""
-rbf =  GPy.kern.rbf(1)
-noise = GPy.kern.white(1)
-kernel = rbf + noise
-Z = np.random.uniform(-3,3,(M,1))
-likelihood = GPy.likelihoods.Gaussian(Y)
-m = GPy.models.sparse_GP(X, likelihood, kernel, Z)
-m.scale_factor=10000
-m.constrain_positive('(variance|lengthscale|precision)')
-m.checkgrad(verbose=1)
-m.optimize('tnc', messages = 1)
-pb.figure()
-m.plot()
-
-variational = m
-"""
-
-# construct kernel
-rbf =  GPy.kern.rbf(1)
-noise = GPy.kern.white(1)
-kernel = rbf + noise
-#Z = np.random.uniform(-3,3,(M,1))
-Z = variational.Z
-likelihood = GPy.likelihoods.Gaussian(Y)
-# create simple GP model
-m = GPy.models.generalized_FITC(X, likelihood, kernel, Z=Z)
-m.constrain_positive('(variance|lengthscale|precision)')
-#m.constrain_fixed('iip')
-m.checkgrad(verbose=1)
-m.optimize('tnc', messages = 1)
-#pb.figure()
-#m.plot()
-"""
-Xnew = X.copy().flatten()
-Xnew.sort()
-Xnew = Xnew[:,None]
-mean,var,low,up = m.predict(Xnew)
-GPy.util.plot.gpplot(Xnew,mean,low,up)
-fitc = m
-"""