Updates

Author: sdemarch

index.html

@@ -258,6 +258,11 @@ <h2 class="page-section-heading d-inline-block text-white">Publications</h2>
                 <!-- 2023 -->
                 <li><h4 class="treeview">2023</h4>
                   <ul class="tw-nested">
+                    <li>
+                        <p class="pre-wrap lead">S. Demarchi, D. Guidotti, L. Pulina and A. Tacchella</p>
+                        <h5>Supporting Standardization of Neural Networks Verification with VNN-LIB and CoCoNet <span class="badge badge-secondary">Conference</span></h5>
+                        <p class="pre-wrap authors">FoMLAS Workshop, Computer-Aided Verification</p>
+                    </li>
                     <li>
                         <p class="pre-wrap lead">S. Demarchi</p>
                         <h5>Experimenting with Constraint Programming Techniques in Artificial Intelligence:
@@ -269,9 +274,6 @@ <h5>Experimenting with Constraint Programming Techniques in Artificial Intellige
                       <h5>Evaluating Reachability Algorithms for Neural Networks on NeVer2 <span class="badge badge-light">Preprint</span></h5>
                       <p class="pre-wrap authors">Submitted for peer review</p>
                     </li>
-
-                    <!-- Journal article: <span class="badge badge-warning">Preprint</span> -->
-
                   </ul>
                 </li>
 
@@ -415,7 +417,7 @@ <h4>Dario Guidotti</h4>
                     <div class="team-member">
                         <img class="mx-auto rounded-circle" src="assets/img/team/sd.jpg" alt="..." />
                         <h4>Stefano Demarchi</h4>
-                        <p class="text-muted">Researcher | UniGE</p>
+                        <p class="text-muted">Post-Doc Researcher | UniGE</p>
                     </div>
                 </div>
             </div>

tutorial_james.html

@@ -182,17 +182,15 @@ <h2 class="page-section-heading text-secondary d-inline-block mb-0">Network Trai
             <div class="text-left font-large">
                 <div id="train-network">
                     <div>
-                        Once the network is completed, you can train it. In the menu bar select "Learn..." -> "Train":
-                        the training window appears, where you can select the dataset and the learning parameters.
-                        We made available the most common datasets directly in the application, but in order to load a
-                        custom dataset some additional steps are required. By selecting <i>Custom Data Source...</i>
-                        in the Dataset box you can load the corresponding file, and fill the dataset parameters dialog.
+                        Once the network is completed, it is time to train it on the dataset. In the menu bar, selecting 
+                        "Learn..." -> "Train" displays the window for the training setup. The first thing to do is to select
+                        the dataset: we made directly available the MNIST and Fashion MNIST datasets, but it is possible to
+                        open any dataset as a text file selecting "Custom data source...".
                         <div class="text-center">
                             <img class="img-tutorial" src="./assets/img/tutorials/james/dataset_load.png" alt="Dataset loading"></img>
                         </div>
-                        In particular, the <i>Target index</i> is the separator between input and output data, i.e.,
-                        the number of inputs. The data type is controlled by a combo box and the delimiter character is
-                        set by default to a comma.
+                        In order to process correctly the dataset, it is required to provide information on the <i>Data type</i>
+                        to expect and the <i>Delimiter</i> character, which are set by default as <i>float</i> and '<i>,</i>'.
                         <div class="text-center">
                             <img class="img-tutorial-wide" src="./assets/img/tutorials/james/training_setup.png" alt="Training parameters of the network"></img>
                         </div>