Image captions changed

MelJan · Apr 22, 2017 · a616fdb · a616fdb
1 parent 690852c
commit a616fdb
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 10 deletions.
diff --git a/docs/tutorials/Binary_RBM_MNIST_small.rst b/docs/tutorials/Binary_RBM_MNIST_small.rst
@@ -10,13 +10,13 @@ Learned filters of a centered binary RBM on the MNIST dataset.
 
 .. figure:: images/BRBM_small_centered_weights.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: weights centered
 
 Sampling results for some examples. The first row shows training data and the following rows are the results after one Gibbs-sampling step starting from the previous row.
 
 .. figure:: images/BRBM_small_centered_samples.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: samples centered
 
 The Log-Likelihood is calculated using the exact Partition function, an annealed importance sampling estimation (optimistic) and reverse annealed importance sampling estimation (pessimistic).
 
@@ -44,13 +44,13 @@ Resulting in the following weights and sampling steps.
 
 .. figure:: images/BRBM_small_normal_weights.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: weights normal
 
 Sampling results for some examples. The first row shows training data and the following rows are the result after one Gibbs-sampling step.
 
 .. figure:: images/BRBM_small_normal_samples.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: samples normal
 
 The Log-Likelihood for this model is significantly worse (8 nats lower).
 
@@ -90,13 +90,13 @@ While the centerer model has a similar performance on the flipped version,
 
 .. figure:: images/BRBM_small_centered_weights_flipped.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: flipped filters centered
 
 Sampling results for some examples. The first row shows training data and the following rows are the result after one Gibbs-sampling step.
 
 .. figure:: images/BRBM_small_centered_samples_flipped.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: flipped samples centered
 
 the normal RBM fails to learn the distribution.
 
@@ -114,11 +114,11 @@ the normal RBM fails to learn the distribution.
 
 .. figure:: images/BRBM_small_normal_weights_flipped.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: flipped filters normal
 
 .. figure:: images/BRBM_small_normal_samples_flipped.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: flipped samples normal
 
 Source code
 ***********

diff --git a/docs/tutorials/ICA_natural_images.rst b/docs/tutorials/ICA_natural_images.rst
@@ -16,13 +16,13 @@ The corresponding whitened image patches.
 
 .. figure:: images/ICA_natural_images_data_whitened.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: 100 gray scale natural image patch examples whitend
 
 The learned filters/independent components learned from the whitened natural image patches.
 
 .. figure:: images/ICA_natural_images_filter.png
    :scale: 75 %
-   :alt: 100 gray scale natural image patch examples
+   :alt: ICA filter on natural images
 
 See `Gaussian-binary restricted Boltzmann machines for modeling natural image statistics. Melchior, J., Wang, N., & Wiskott, L.. (2017). PLOS ONE, 12(2), 1–24. <http://doi.org/10.1371/journal.pone.0171015>`_
 for a analysis of ICA and GRBM.