note test and training set

[asr1617.git] / methods.tex

diff --git a/methods.tex b/methods.tex
index 45b677e..96ee578 100644 (file)
--- a/methods.tex
+++ b/methods.tex
@@ -178,7 +178,8 @@ in Equation~\ref{eq:softmax}.
 
 The data is shuffled before fed to the network to mitigate the risk of
 overfitting on one album. Every model was trained using $10$ epochs and a
-batch size of $32$.
+batch size of $32$. The training set and test set are separated by taking a
+$90\%$ slice of all the data.
 
 \begin{equation}\label{eq:relu}
        f(x) = \left\{\begin{array}{rcl}