[FIX] set transparent bg for imgs

docs/Intro/Basics.rst

@@ -13,7 +13,7 @@ which in turn revise the outcomes of the machine learning model, and then
 fed back into the machine learning model for further training. 
 To implement this process, the following four steps are necessary:
 
-.. image:: ../img/ABL-Package.jpg
+.. image:: ../img/ABL-Package.png
 
 1. Prepare datasets
 
@@ -38,7 +38,3 @@ To implement this process, the following four steps are necessary:
 
     Use ``SimpleBridge`` to bridge the machine learning and reasoning part
     for integrated training and testing. 
-
-
-
-

docs/Intro/Quick Start.rst

@@ -54,8 +54,8 @@ Afterward, we wrap it in ``ABLModel``.
 
 Read more about `build machine learning models <Learning.html>`_.
 
-Reasoning (Map pseudo labels to reasoning results)
---------------------------------------------------
+Build the Reasoning Part
+------------------------
 
 First, we build a knowledge base that defines how to deduce 
 logical results (i.e., calculate summation) from the pseudo labels 

docs/Overview/Abductive Learning.rst

@@ -10,7 +10,7 @@ instance, :math:`y_i \in \mathcal{Y}` is the corresponding ground-truth
 label. These data are then used to train a classifier model :math:`f:
 \mathcal{X} \mapsto \mathcal{Y}` to accurately predict the unseen data.
 
-.. image:: ../img/ML.jpg
+.. image:: ../img/ML.png
    :width: 600px
 
 In **Abductive Learning (ABL)**, we assume that, in addition to data as
@@ -47,7 +47,7 @@ base.
 
 The following figure illustrates this process:
 
-.. image:: ../img/ABL.jpg
+.. image:: ../img/ABL.png
    :width: 800px
 
 We can observe that in the above figure, the left half involves machine

docs/README.rst

@@ -8,7 +8,7 @@ dual-driven (data & knowledge driven) learning system, integrating and
 balancing the use of machine learning and logical reasoning in a unified
 model.
 
-.. image:: img/ABL.jpg
+.. image:: img/ABL.png
 
 Installation
 ------------