dekker.one
Group work for a Monash Research Methods course
Add paragraph on random forest
+8
-1
+8
-1
mini_proj/report/waldo.tex
+8
-1
mini_proj/report/waldo.tex
···
154
154
155
155
\paragraph{Random Forest}
156
156
157
-
\cite{randomforest}
157
+
\cite{randomforest} is a method that is based on classifications decision
158
+
trees. In a decision tree a new instances is classified by going down a
159
+
(binary) tree. Each non-leaf node contain a selection criteria to its
160
+
branches. Every leaf node contains the class that will be assigned to the
161
+
instance if the node is reached. In other training methods, decision trees
162
+
have the tendency to overfit, but in random forest a multitude of decision
163
+
tree is trained with a certain degree of randomness and the mean of these
164
+
trees is used which avoids this problem.
158
165
159
166
\subsection{Neural Network Architectures}
160
167
\todo{Did we only do the three in the end? (Alexnet?)}