From c25dc4a42966d7d3af6e9a434a7e403ebd92a48c Mon Sep 17 00:00:00 2001 From: Mart Lubbers Date: Sat, 10 Jun 2017 20:30:54 +0200 Subject: [PATCH] typos --- conclusion.tex | 6 +++--- rutitlepage | 1 + todo.txt | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) create mode 160000 rutitlepage create mode 100644 todo.txt diff --git a/conclusion.tex b/conclusion.tex index 3adbc05..3cc834f 100644 --- a/conclusion.tex +++ b/conclusion.tex @@ -11,7 +11,7 @@ similarly. To determine whether the model generalizes, alien data has been offered to the model to see how it performs. It was shown that for similar singing styles the models perform similar. The alien data offered containing different singing -styles, atmospheric noise and accompaniment is classified less good. +styles, atmospheric noise and accompaniment is classified worse. From the results we can conclude that the model generalizes well over the trainings set, even with little hidden nodes. The models with 3 or 5 hidden @@ -25,8 +25,8 @@ performance. The dataset used only contains three albums and might not be considered varied. However, the albums are picked to represent the ends of the growling spectrum. Therefore the resulting model can be very general. On the other side, it could -also result in a model that is overfitted the three islands in entire space of -grunting voices. +also result in a model that is overfitted to the three islands in the entire +space of grunting voices. In this case it seems that the model generalizes well. The alien data --- similar to the training data --- offered to the model, results in a good performance. diff --git a/rutitlepage b/rutitlepage new file mode 160000 index 0000000..32fc745 --- /dev/null +++ b/rutitlepage @@ -0,0 +1 @@ +Subproject commit 32fc745524953baa115b829fd37a88c934ed1330 diff --git a/todo.txt b/todo.txt new file mode 100644 index 0000000..b3aa4a1 --- /dev/null +++ b/todo.txt @@ -0,0 +1 @@ +performance over time -- 2.20.1