diff --git a/doc/guide.rst b/doc/guide.rst
index d0d6b018754b50c96364ea2143e5f2fd53f76be0..39059333dafc3882db74b49afd5babc94616972c 100644
--- a/doc/guide.rst
+++ b/doc/guide.rst
@@ -276,7 +276,7 @@ prior GMM.
     >>> gmm_stats = prior_gmm.acc_stats(data)
     >>> # Printing the responsibilities
     >>> print(gmm_stats.n/gmm_stats.t)
-     [0.6  0.4]
+     [0.4  0.6]
 
 
 Inter-Session Variability
@@ -322,7 +322,7 @@ The snippet bellow shows how to:
    >>> import bob.learn.em
    >>> import numpy as np
 
-   >>> np.random.seed(10)
+   >>> np.random.seed(9)
 
    >>> # Generating some fake data
    >>> data_class1 = np.random.normal(0, 0.5, (10, 3))
@@ -341,13 +341,13 @@ The snippet bellow shows how to:
    >>> enroll_data = np.array([[1.2, 0.1, 1.4], [0.5, 0.2, 0.3]])
    >>> model = isv_machine.enroll_using_array(enroll_data)
    >>> print(model)
-     [[ 0.54   0.246  0.505  1.617 -0.791  0.746]]
+     [[ 0.399  0.281  0.353  2.778 -1.319  0.876]]
 
    >>> # Probing
    >>> probe_data = np.array([[1.2, 0.1, 1.4], [0.5, 0.2, 0.3]])
    >>> score = isv_machine.score_using_array(model, probe_data)
    >>> print(round(score, 3))
-     2.754
+     7.459
 
 
 
@@ -403,12 +403,12 @@ such session variability model.
    >>> enroll_data = np.array([[1.2, 0.1, 1.4], [0.5, 0.2, 0.3]])
    >>> model = jfa_machine.enroll_using_array(enroll_data)
    >>> print(model)
-     (array([0.634, 0.165]), array([ 0.,  0.,  0.,  0., -0.,  0.]))
+     (array([1.569, 0.06 ]), array([ 0., -0.,  0., -0.,  0.,  0.]))
 
    >>> probe_data = np.array([[1.2, 0.1, 1.4], [0.5, 0.2, 0.3]])
    >>> score = jfa_machine.score_using_array(model, probe_data)
    >>> print(round(score, 3))
-     0.471
+     6.084