graphs:
dot -Teps d1.dot > d1.eps
+ dot -Teps d2.dot > d2.eps
clean:
rm -vf *.eps report.{aux,out,dvi,log,pyg,toc,eps,synctex.gz}
\frac{3}{19600}\approx0.000153$
\section{Bayesian networks}
+A bayesian network representation of the burglary problem with a multitude of
+houses and burglars is possible but would be very big and tedious because all
+the constraints about the burglars must be incorporated in the network.
+The network would look something like this:
+\begin{figure}[H]
+ \caption{Bayesian network of burglars and houses}
+ \label{bnetwork21}
+ \centering
+ \includegraphics[scale=0.5]{d2.eps}
+\end{figure}