fixed documentation

NEGU93 · Mar 12, 2021 · 004f29c · 004f29c
1 parent 348080e
commit 004f29c
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 4 deletions.
diff --git a/cvnn/_version.py b/cvnn/_version.py
@@ -1 +1 @@
-__version__ = '1.1.10'
+__version__ = '1.1.11'
diff --git a/docs/experiments/correlation_noise.rst b/docs/experiments/correlation_noise.rst
@@ -16,11 +16,10 @@ This results can be replicated by running the following code (changing the input
 .. note:: Results will be differents to those published on the report because of the following reasons
 
     - Since version 0.2.89 the default real mlp model changed using a new definition that will be published in a new article.
+    - Since version 0.3.48 cvnn started using TensorFlow optimizer which averages gradients by it's batch size according to `this post <https://stackoverflow.com/questions/66566905/debugging-tensorflow-fit-not-making-sense/>`_. This `issue <https://github.com/tensorflow/tensorflow/issues/47702>`_ was raised officially.
     - Default optimizer changed to adam.
     - As the dataset is generated randomly. This means two independent runs of :code:`run_gaussian_dataset_montecarlo` may not have the same confidence intervals and results.
-        - The error reported on the paper is for the specific dataset generated. 
         - Disclaimer: All comparisons with a parameter variation was done with the same dataset.
-    - Since version 0.3.48 cvnn started using TensorFlow optimizer which averages gradients by it's batch size according to `this post <https://stackoverflow.com/questions/66566905/debugging-tensorflow-fit-not-making-sense/>`_
 
 **Simulation Results**
 

diff --git a/docs/index.rst b/docs/index.rst
@@ -3,7 +3,7 @@ Complex-Valued Neural Network (CVNN)
 ====================================
 
 :Author:  J. Agustin Barrachina
-:Version: 1.1.10 of 03/11/2021
+:Version: 1.1.11 of 03/12/2021
 
 
 Content