small update to project 2

doc/Projects/2019/Project2/html/Project2-bs.html

@@ -153,7 +153,7 @@ MathJax.Hub.Config({
 <center><b>Department of Physics, University of Oslo, Norway</b></center>
 <br>
 <p>
-<center><h4>Oct 2, 2019</h4></center> <!-- date -->
+<center><h4>Oct 9, 2019</h4></center> <!-- date -->
 <br>
 <p>
 </div> <!-- end jumbotron -->
@@ -265,7 +265,7 @@ Discuss again your choice of cost function.
 
 <p>
 Train your network and compare the results with those from your Logistic  Regression code. 
-You can test your results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
+You should test your results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
 
 <p>
 Comment your results and give a critical discussion of the results
@@ -290,10 +290,17 @@ project 1.
 Compare you results from the neural network regression analysis (with a discussion of learning rates and regularization parameters)
 with those you obtained in project 1. Alternatively, if you opt for other data sets, you would need to run your standard ordinary least squares, Ridge and Lasso calculations using your codes from project 1.
 
+<p>
+Again, we strongly recommend that you compare your own neural Network code and results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
+
 <h3 id="___sec5" class="anchor">Part e) Critical evaluation of the various algorithms </h3>
 
 <p>
-After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes can also be part of your final project 3, but now applied to other data sets.
+After all these glorious calculations, you should now summarize the
+various algorithms and come with a critical evaluation of their pros
+and cons. Which algorithm works best for the regression case and which
+is best for the classification case. These codes can also be part of
+your final project 3, but now applied to other data sets.
 
 <h2 id="___sec6" class="anchor">Background literature </h2>
 

doc/Projects/2019/Project2/html/Project2.html

@@ -112,7 +112,7 @@ MathJax.Hub.Config({
 <center><b>Department of Physics, University of Oslo, Norway</b></center>
 <br>
 <p>
-<center><h4>Oct 2, 2019</h4></center> <!-- date -->
+<center><h4>Oct 9, 2019</h4></center> <!-- date -->
 <br>
 
 <h2 id="___sec0">Classification and Regression, from linear and logistic regression to neural networks  </h2>
@@ -222,7 +222,7 @@ Discuss again your choice of cost function.
 
 <p>
 Train your network and compare the results with those from your Logistic  Regression code. 
-You can test your results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
+You should test your results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
 
 <p>
 Comment your results and give a critical discussion of the results
@@ -247,10 +247,17 @@ project 1.
 Compare you results from the neural network regression analysis (with a discussion of learning rates and regularization parameters)
 with those you obtained in project 1. Alternatively, if you opt for other data sets, you would need to run your standard ordinary least squares, Ridge and Lasso calculations using your codes from project 1.
 
+<p>
+Again, we strongly recommend that you compare your own neural Network code and results against a similar code using <b>Scikit-Learn</b> (see the examples in the above lecture notes) or <b>tensorflow/keras</b>.
+
 <h3 id="___sec5">Part e) Critical evaluation of the various algorithms </h3>
 
 <p>
-After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes can also be part of your final project 3, but now applied to other data sets.
+After all these glorious calculations, you should now summarize the
+various algorithms and come with a critical evaluation of their pros
+and cons. Which algorithm works best for the regression case and which
+is best for the classification case. These codes can also be part of
+your final project 3, but now applied to other data sets.
 
 <h2 id="___sec6">Background literature </h2>
 

doc/Projects/2019/Project2/pdf/Project2.p.tex

@@ -149,7 +149,7 @@ Project 2 on Machine Learning, deadline November 8
 
 % --- begin date ---
 \begin{center}
-Oct 2, 2019
+Oct 9, 2019
 \end{center}
 % --- end date ---
 
@@ -255,7 +255,7 @@ to use the codes in the above lecture slides as starting points.
 Discuss again your choice of cost function.
 
 Train your network and compare the results with those from your Logistic  Regression code. 
-You can test your results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
+You should test your results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
 
 Comment your results and give a critical discussion of the results
 obtained with the Logistic Regression code and your own Neural Network
@@ -276,8 +276,16 @@ project 1.
 Compare you results from the neural network regression analysis (with a discussion of learning rates and regularization parameters)
 with those you obtained in project 1. Alternatively, if you opt for other data sets, you would need to run your standard ordinary least squares, Ridge and Lasso calculations using your codes from project 1.
 
+Again, we strongly recommend that you compare your own neural Network code and results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
+
+
+
 \paragraph{Part e) Critical evaluation of the various algorithms.}
-After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes can also be part of your final project 3, but now applied to other data sets.
+After all these glorious calculations, you should now summarize the
+various algorithms and come with a critical evaluation of their pros
+and cons. Which algorithm works best for the regression case and which
+is best for the classification case. These codes can also be part of
+your final project 3, but now applied to other data sets.
 
 
 

doc/Projects/2019/Project2/pdf/Project2.tex

@@ -123,7 +123,7 @@ Project 2 on Machine Learning, deadline November 8
 
 % --- begin date ---
 \begin{center}
-Oct 2, 2019
+Oct 9, 2019
 \end{center}
 % --- end date ---
 
@@ -229,7 +229,7 @@ to use the codes in the above lecture slides as starting points.
 Discuss again your choice of cost function.
 
 Train your network and compare the results with those from your Logistic  Regression code. 
-You can test your results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
+You should test your results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
 
 Comment your results and give a critical discussion of the results
 obtained with the Logistic Regression code and your own Neural Network
@@ -250,8 +250,16 @@ project 1.
 Compare you results from the neural network regression analysis (with a discussion of learning rates and regularization parameters)
 with those you obtained in project 1. Alternatively, if you opt for other data sets, you would need to run your standard ordinary least squares, Ridge and Lasso calculations using your codes from project 1.
 
+Again, we strongly recommend that you compare your own neural Network code and results against a similar code using \textbf{Scikit-Learn} (see the examples in the above lecture notes) or \textbf{tensorflow/keras}. 
+
+
+
 \paragraph{Part e) Critical evaluation of the various algorithms.}
-After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes can also be part of your final project 3, but now applied to other data sets.
+After all these glorious calculations, you should now summarize the
+various algorithms and come with a critical evaluation of their pros
+and cons. Which algorithm works best for the regression case and which
+is best for the classification case. These codes can also be part of
+your final project 3, but now applied to other data sets.
 
 
 

doc/src/Projects/2019/Project2/Project2.do.txt

@@ -93,7 +93,7 @@ to use the codes in the above lecture slides as starting points.
 Discuss again your choice of cost function.
 
 Train your network and compare the results with those from your Logistic  Regression code. 
-You can test your results against a similar code using _Scikit-Learn_ (see the examples in the above lecture notes) or _tensorflow/keras_. 
+You should test your results against a similar code using _Scikit-Learn_ (see the examples in the above lecture notes) or _tensorflow/keras_. 
 
 Comment your results and give a critical discussion of the results
 obtained with the Logistic Regression code and your own Neural Network
@@ -115,9 +115,17 @@ project 1.
 Compare you results from the neural network regression analysis (with a discussion of learning rates and regularization parameters)
 with those you obtained in project 1. Alternatively, if you opt for other data sets, you would need to run your standard ordinary least squares, Ridge and Lasso calculations using your codes from project 1.
 
+Again, we strongly recommend that you compare your own neural Network code and results against a similar code using _Scikit-Learn_ (see the examples in the above lecture notes) or _tensorflow/keras_. 
+
+
+
 === Part e) Critical evaluation of the various algorithms ===
 
-After all these glorious calculations, you should now summarize the various algorithms and come with a critical evaluation of their pros and cons. Which algorithm works best for the regression case and which is best for the classification case. These codes can also be part of your final project 3, but now applied to other data sets.
+After all these glorious calculations, you should now summarize the
+various algorithms and come with a critical evaluation of their pros
+and cons. Which algorithm works best for the regression case and which
+is best for the classification case. These codes can also be part of
+your final project 3, but now applied to other data sets.