updates

Author: msneubauer

_sources/projects/Project_01_AberratedImages.ipynb

@@ -406,7 +406,7 @@
     "\n",
     "* Initial version: Max Gold with some guidance from Mark Neubauer\n",
     "\n",
-    "© Copyright 2024"
+    "© Copyright 2026"
    ]
   }
  ],

_sources/projects/Project_01_DarkEnergySurvey.ipynb

@@ -318,7 +318,7 @@
         "\n",
         "* Initial version: Ferzem Khan with some guidance from Mark Neubauer\n",
         "\n",
-        "© Copyright 2024"
+        "© Copyright 2026"
       ]
     }
   ],

_sources/projects/Project_01_ExoticParticles.ipynb

@@ -269,7 +269,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Implement and train a shallow neural network (NN) described in ref [[1]](https://arxiv.org/abs/1402.4735) for one of the exotic particle hypotheses. You should implement a NN one that makes the training time manageable, like one of the shallow networks with hyperparameters shown in Table 2 of ref [[1]](https://arxiv.org/abs/1402.4735) or even a smaller network. Can you generate and show the NN classification outputs for this network?"
+    "First implement and train a shallow neural network (NN) described in ref __[<span style=\"color:Red\">1</span>]__ for one of the exotic particle hypotheses. You should implement a NN one that makes the training time manageable on a CPU, like one of the shallow networks with hyperparameters shown in Table 2 of ref __[<span style=\"color:Red\">1</span>]__ or even a smaller network. Next train a fully-connected deep neural network (DNN) using a GPU by increasing the number of hidden layers and neuron within the layers. The exact DNN setup is up to you, as long as it has meaningfully more trainable parameters than the shallow NN from the first part. Show the classification output for signal and background for both networks, as well as the ROC curve and AUC metric."
    ]
   },
   {
@@ -291,7 +291,7 @@
     "\n",
     "* Initial version: Mark Neubauer\n",
     "\n",
-    "© Copyright 2024"
+    "© Copyright 2026"
    ]
   }
  ],

_sources/projects/Project_01_GalaxyZoo.ipynb

@@ -203,7 +203,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Each Image is labeled with its GalaxyID. Use the benchmark data set as the classification label. Since the training data is the Image, we could use a Convolutional Neural Network (CNN) architecture to build up the training. What is the input data for your Network? Can you design and demonstrate a simple CNN structure for this training?"
+    "Each Image is labeled with its GalaxyID. Use the benchmark data set as the classification label. Since the training data is images, a Convolutional Neural Network (CNN) architecture is an appropriate model for galaxy classification. Design, describe and implement a simple CNN and use it to demonstrate galaxy classification for this dataset. What is the input data for your Network? How well does your model perform?"
    ]
   },
   {
@@ -223,7 +223,7 @@
     "\n",
     "* Initial version: Mark Neubauer\n",
     "\n",
-    "© Copyright 2024"
+    "© Copyright 2026"
    ]
   }
  ],

_sources/projects/Project_01_GravitationalWaves.ipynb

@@ -514,7 +514,7 @@
         "\n",
         "* Initial version: Mark Neubauer\n",
         "\n",
-        "© Copyright 2025"
+        "© Copyright 2026"
       ]
     }
   ],

_sources/projects/Project_01_HiggsTauTau.ipynb

@@ -196,7 +196,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Implement and train one of the neural networks (NN) described in [[1]](https://papers.nips.cc/paper/2014/hash/e1d5be1c7f2f456670de3d53c7b54f4a-Abstract.html). Be sure to set aside test data from the original data set which is not used in the training. You should implement a NN one that makes the training time manageable, like one of the shallow networks with hyperparameters shown in Table 1 of [[1]](https://papers.nips.cc/paper/2014/hash/e1d5be1c7f2f456670de3d53c7b54f4a-Abstract.html) or even a smaller network. Can you show the NN classification output (analogous to Figure 4)?"
+    "Implement and train one of the neural networks (NN) described in __[<span style=\"color:Red\">1</span>]__. Be sure to set aside test data from the original data set which is not used in the training. First implement a shallow NN one that makes the training time manageable on a CPU, like one of the shallow networks with hyperparameters shown in Table 1 of __[<span style=\"color:Red\">1</span>]__ or even a smaller network. Next train a fully-connected deep neural network (DNN) using a GPU by increasing the number of hidden layers and neuron within the layers. The exact DNN setup is up to you, as long as it has meaningfully more trainable parameters than the shallow NN from the first part. Show the classification output for signal and background (analogous to Figure 4) for both networks, as well as the ROC curve and AUC metric."
    ]
   },
   {
@@ -216,7 +216,7 @@
     "\n",
     "* Initial version: Mark Neubauer\n",
     "\n",
-    "© Copyright 2024"
+    "© Copyright 2026"
    ]
   }
  ],

_sources/projects/Project_01_NuclearGeometryQGP.ipynb

@@ -241,7 +241,7 @@
     "\n",
     "* Initial version: Anne Sickles\n",
     "\n",
-    "© Copyright 2024"
+    "© Copyright 2026"
    ]
   }
  ],