Modified emojis

docs/source/index.rst

@@ -6,10 +6,11 @@ The ``autoqild`` Python package
      <a href="https://arxiv.org/abs/2401.14283" style="float: right; margin-left: 20px; margin-bottom: 10px;">
        <img src="logo.png" alt="Paper" width="200" height="200">
      </a>
-     <p style="text-align: justify;">
-       The <strong>AutoMLQuantILDetect</strong> package utilizes AutoML approaches to detect and quantify system information leakage. It is an advanced toolkit that leverages the power of Automated Machine Learning (AutoML) to quantify information leakage accurately. This package estimates mutual information (MI) within systems that release classification datasets. By leveraging state-of-the-art statistical tests, it precisely quantifies mutual information (MI) and effectively detects information leakage within classification datasets. With <strong>AutoMLQuantILDetect</strong>, users can confidently and comprehensively address the critical challenges of quantification and detection in information leakage analysis.
-     </p>
    </div>
+The **AutoMLQuantILDetect** package utilizes AutoML approaches to detect and quantify system information leakage.
+It is an advanced toolkit that leverages the power of Automated Machine Learning (AutoML) to quantify information leakage accurately.
+This package estimates mutual information (MI) within systems that release classification datasets.
+By leveraging state-of-the-art statistical tests, it precisely quantifies mutual information (MI) and effectively detects information leakage within classification datasets. With <strong>AutoMLQuantILDetect</strong>, users can confidently and comprehensively address the critical challenges of quantification and detection in information leakage analysis.
 
 Contents
 ~~~~~~~~
@@ -25,12 +26,12 @@ Contents
    :maxdepth: 1
    :caption: TUTORIALS
 
-   notebooks/comparing_mi_estimators
-   notebooks/automated_information_leakage_detection
+   🟠⬤ notebooks/comparing_mi_estimators
+   🟠⬤ notebooks/automated_information_leakage_detection
 
 .. toctree::
    :maxdepth: 2
-   :caption: API REFERENCE
+   :caption: API DOCS
 
    api
 

docs/source/installation.rst

@@ -1,5 +1,5 @@
-Installation Guide
-==================
+🛠️ Installation Guide
+=====================
 
 .. note::
     `AutoMLQuantILDetect` with package ``autoqild`` is intended to work with **Python 3.9.5 and above**.

docs/source/references.rst

@@ -1,12 +1,12 @@
-📚🔖Bibliography
-===============
+📚 Litereture Research
+======================
 
 List of references for the implemented learning algorithms, AutoML tools and baseline mutual information estimators
 
 
-^^^^^^^^^^^^^^^^^^^^^^
+----------------------
 📊 Learning Algorithms
-^^^^^^^^^^^^^^^^^^^^^^
+----------------------
 - `Multi-Layer Perceptron (MLP) <https://www.researchgate.net/publication/35657389_Beyond_regression_new_tools_for_prediction_and_analysis_in_the_behavioral_sciences>`_: Werbos (1974)
 - `Consistency MLP <https://dl.acm.org/doi/10.1016/S0893-6080(09)80011-7>`_: Mielniczuk et al. (1993)
 - `Random Forest (RF) <https://doi.org/10.1023/A:1010933404324>`_: Breiman (2001)
@@ -17,14 +17,14 @@ List of references for the implemented learning algorithms, AutoML tools and bas
 - `Classifier Calibration <https://dl.acm.org/doi/10.1007/s10994-023-06336-7>`_: Filho et al. (2023)
 
 
-^^^^^^^^^^^^^^^^
+----------------
 🤖 AutoML Tools
-^^^^^^^^^^^^^^^^
+----------------
 - `TabPFN <https://arxiv.org/abs/2207.01848>`_: Hollmann et al. (2023)
 - `AutoGluon <https://arxiv.org/abs/2003.06505>`_: Erickson et al. (2022)
 
-^^^^^^^^^^^^^^^^^^^^^^^^^^
+-------------------------
 🚀 Baseline MI Estimators
-^^^^^^^^^^^^^^^^^^^^^^^^^^
+-------------------------
 - `Mutual Information Neural Estimation (MINE) <https://proceedings.mlr.press/v80/belghazi18a/belghazi18a.pdf>`_: Belghazi et al. (2018)
 - `PC-softmax <https://arxiv.org/abs/1911.10688>`_: Qin et al. (2020)

docs/source/start.rst

@@ -1,5 +1,5 @@
-Quickstart Guide
-================
+⚙️ Quickstart Guide
+===================
 
 You can use `AutoMLQuantILDetect` in different ways.
 There already exist quite some classifiers and AutoML tools which can be used to estimate mutual information using the log-loss and the accuracy of the learned model.