final version

[ker2014-2.git] / report / ass2-2.tex

diff --git a/report/ass2-2.tex b/report/ass2-2.tex
index a3ba388..bdb504a 100644 (file)
--- a/report/ass2-2.tex
+++ b/report/ass2-2.tex
@@ -1,16 +1,17 @@
 \chapter{Visual representations and reasoning}
 We chose pizzas for our domain, as everybody likes pizzas. We chose to have six different pizzas. As all pizzas have tomato sauce and cheese, we didn't take those into account. Below we listed all the pizzas and their ingredients.
 \begin{itemize}
-       \item Margherita; basilicum
-       \item Hawaii; ham, pineapple and basilicum
-       \item Salami; salami and basilicum
+       \item Margherita; basil
+       \item Hawaii; ham, pineapple and basil
+       \item Salami; salami and basil
        \item Funghi; mushrooms and ham
        \item Pepperoni; salami and jalape\~nos
 \end{itemize}
 
-We are able to observe different kind of shapes; circles, double circles (like tires or olives in our case), squares and blobs. 
+We are able to observe different kind of shapes; circles, double circles (like tires or olives in our case), squares and blobs. For each shape it is possible that it represents different ingredients. Because of this we defined for every shape the probabilities that it is a particular ingredient. For example a circle could be basil, salami or mozarella with respectively probabilities of 0.2, 0.4 and 0.4. The probability that basil is observed is then composed out of the probability that you observed a 'basil' circle and the probability that you have actually observed a circle.
+
+Our style of reasoning that we employed is deductive. %Iets met vanuit een knowledgebase redeneren en vanuit hypotheses ofzo?
 
-Our style of reasoning that we employed is deductive. 
 \iffalse
 TODO
 In a more structured way, you are required to describe clearly and fully:
@@ -28,7 +29,7 @@ real-time operation.
 \fi
 \section{Domain representation}
 Translating the domain specification to AILog results in the following AILog
-code:
+code:\\
 \inputminted[linenos,fontsize=\footnotesize]{prolog}{./src/pizza.ail}
 
 \section{Queries}
@@ -47,11 +48,11 @@ ailog: predict circlePresent.
 Answer: P(circlePresent|Obs)=0.95.
        [ok,more,explanations,worlds,help]: ok.
 \end{minted}
-\begin{table}
+\begin{table}[H]
        \label{chances}
        \begin{tabular}{|l|ll|}
                \hline
-               & Observed\\
+               & Observed &\\
                Present & T & F\\
                \hline
                T & $0.95$ & $0.01$\\
@@ -97,12 +98,12 @@ every possible explanations to find out how the most likely world looks like:
 ailog: predict whatpizza.
 Answer: P(whatpizza|Obs)=[0.19251740120000002,0.19278577620000004].
   [ok,more,explanations,worlds,help]: explanations.
-  0: ass([],[basilicumcircle,circle,doublecircle,doublecircleOlives,noObserveError],9.5e-6)
+  0: ass([],[basilcircle,circle,doublecircle,doublecircleOlives,noObserveError],9.5e-6)
   1: ass([],[circle,doublecircle,doublecircleJalapenos,noObserveError,salamicircle],1.9e-5)
   2: ass([],[blob,blobHam,blobMushrooms,circle,funghiham,noObserveError],3.3249999999999995e-6)
-  3: ass([],[basilicumcircle,circle,noObserveError,salamibasilicum,salamicircle],7.6e-5)
-  4: ass([],[basilicumcircle,circle,noObserveError],0.0019)
-  5: ass([],[blob,blobBasilicum,circle,noObserveError],9.5e-6)
+  3: ass([],[basilcircle,circle,noObserveError,salamibasil,salamicircle],7.6e-5)
+  4: ass([],[basilcircle,circle,noObserveError],0.0019)
+  5: ass([],[blob,blobbasil,circle,noObserveError],9.5e-6)
   [ok,more,how i,help]: how 4.
    whatpizza <-
       1: p_margarita
@@ -116,8 +117,8 @@ ailog: predict whatpizza.
 Answer: P(whatpizza|Obs)=[0.28994000000000003,0.33126500000000003].
   [ok,more,explanations,worlds,help]: explanations.
   0: ass([],[blob,blobHam,blobMushrooms,circle,funghiham,noObserveError],3.3249999999999995e-6)
-  1: ass([],[basilicumcircle,blob,circle,noObserveError],1.9e-5)
-  2: ass([],[blob,blobBasilicum,circle,noObserveError],9.5e-6)
+  1: ass([],[basilcircle,blob,circle,noObserveError],1.9e-5)
+  2: ass([],[blob,blobbasil,circle,noObserveError],9.5e-6)
   [ok,more,how i,help]: how 0.
    whatpizza <-
       1: p_funghi
@@ -125,3 +126,14 @@ Answer: P(whatpizza|Obs)=[0.28994000000000003,0.33126500000000003].
 \end{minted}
 
 \section{Reflections}
+The model is relatively effective. One can easily compute the most likely pizza
+configuration from abstract shapes only. The model is also very scalable since
+the model only grows with the number of ingredients per pizza added because all
+the pizzas are independent. Because of this, large datasets can be added very
+easily and because of this the computational complexity does not increase very
+much. Changes in parameters can also be added very easily, for example when a
+more accurate low level detection technique is applied the probabilities for
+the shapes present can be increased very easily.
+
+\section{Additional Questions}
+If we could change a thing about the second assignment, we would try to make it slightly less abstract what the meaning of the assignment was. We estimate that we spent about 14 hours each on the assignment.