diff --git a/README.md b/README.md
index db5aeda..adc4165 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 # Description
-`robocode-svm` is a script to demonstrate Support Vector Machine (SVM) classification on outcomes of the battles of Robocode.
+`robocode-svm` is a script to demonstrate Support Vector Machine (SVM) classification on outcomes of the battles of Robocode. You can check the original assignment tht led to this work [here](https://github.com/delmadord/robocode_svm/blob/master/extras/assignment.pdf).
 
 # Installation
 The script runs under Linux and requires `robocode`, `svm-scale`, `svm-train` and `svm-predict` executables located in the `PATH`. On Arch Linux (or it's derivative, like i.e. Manjaro), this can be achieved by installing [libsvm](https://aur.archlinux.org/packages/libsvm/) and [robocode](https://aur.archlinux.org/packages/robocode/) from AUR (if enabled) by following command (or equivalent)
@@ -23,6 +23,13 @@ USAGE: robocode-svm --battle x y [alpha]
   -h,--help		Show this help
 ```
 
-# Extras
-* [assignment](https://github.com/delmadord/robocode_svm/blob/master/extras/assignment.pdf) 
-* [2D visualisation](https://github.com/delmadord/robocode_svm/blob/master/extras/visualize2D.png) **sample** - the *alpha* parameter (initial gun orientation) was omitted.
+# Details
+The robots on test are **sample.Corners**(starting in center) and **sample.TrackFire**(roaming). The *gun cooling rate* is set to **0.07**. These were obtained by experimenting and provide great outcomes on the battlefied, that can be classified easily.  
+
+## SVM kernel parameters
+The SVM type used is **C-SVC** (multi-class classification), with the **radial babsis** kernel. The *cost* parameter C is **10** and the *sigma* parameter is **2**. You can find more details about these at [libsvm home](https://github.com/cjlin1/libsvm).
+
+## 2D visualisation
+When the third parameter (initial gun orientation) of the roaming robot is omitted, we can generate *sample* visualisation of the result of this classification. Our experiments were indicating, that this parameter has low (about 2%) significance on the output of the battle.
+
+![2D visualisation](https://github.com/delmadord/robocode_svm/blob/master/extras/visualize2D.png)
diff --git a/extras/visualize2D.png b/extras/visualize2D.png
index cb17bc1..5743015 100644
--- a/extras/visualize2D.png
+++ b/extras/visualize2D.png
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1dcfaa0b423bc755addfde5f33bf758391f98131d998d5641626cb5cd5cbcbc
-size 13488
+oid sha256:49b456347bda2dd9d778260a85cb772069ac5b14ea9a03e40382414550676b8b
+size 13536
diff --git a/robocode-svm b/robocode-svm
index 932df73..fec9b7c 100755
--- a/robocode-svm
+++ b/robocode-svm
@@ -22,7 +22,7 @@ robot2="sample.Fire"
 # Requires a function because of two points where it is called
 show_help() {
 	echo "Generate the data required for SVM classification and show the accuracy"
-	echo "of the generated SVM model. If coordinates are supported, one visual battle"
+	echo "of the generated SVM model. If coordinates are provided, one visual battle"
 	echo "is shown to support the prediction."
 	echo ""
 	echo "USAGE: robocode-svm ACTION"