small cleanup

Author: derpierdude

content/Unit 4/Artificial Intelligence/Artificial Intelligence.md

@@ -12,7 +12,7 @@ AIs 'create'/train their own algorithm given input and (most of the time) expect
 
 ## Machine learning
 A sub-type of AI that "learns" from data to make predictions and classifications, given new information.
-See [[Types of Machine Learning|types of machine learning.]]
+See [[Training with Data (Types of machine learning)|types of machine learning.]]
 ## Research
 It is a field of research in computer science that develops and studies methods and software that enable machines to perceive their environment, and use learning and intelligence to take actions that maximise their chances of achieving defined goal. 
 ## Examples

content/Unit 4/Artificial Intelligence/Machine Learning/Classification/Classification types/Linear classification/Linear Classification.md

@@ -22,5 +22,4 @@ More specifically
 	- $h(x)=1$
 - **Class -1 boundary**
 	- $h(x)=-1$
-The margin for this pair of margin boundaries is $m=\frac{2}{||w||}$
-($||w||$ is magnitude of vector $w$, it is the more formal (?) version of VCE spesh's $|w|$)
+The margin for this pair of margin boundaries is $m=\frac{2}{||w||}$, where $||w||$ is the magnitude of the weights (distance from the origin)

content/Unit 4/Artificial Intelligence/Machine Learning/Classification/Classification types/Linear classification/Margin boundaries (Linear).md

@@ -1,3 +1,3 @@
- A kernel trick involve using linear classifiers to solve non linear problems.
+A kernel trick involves using linear classifiers to solve non linear problems.
 Named from the use of kernel functions.
 Involves introducing a new feature derived from preexisting features (see [[Feature modification]]).

…Learning/Featues/Feature modification.md …earning/Features/Feature modification.mdcontent/Unit 4/Artificial Intelligence/Machine Learning/Featues/Feature modification.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Feature modification.md content/Unit 4/Artificial Intelligence/Machine Learning/Featues/Feature modification.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Feature modification.md

@@ -1,4 +1,4 @@
-A [[Types of Machine Learning|supervised]] machine learning model that assigns data points to categories by finding a linear decision boundary (a line in 2D, a plane in 3D, and a hyperplane in above 3 dimensions) to seperate them.
+A [[Model training|]] machine learning model that assigns data points to categories by finding a linear decision boundary (a line in 2D, a plane in 3D, and a hyperplane in above 3 dimensions) to seperate them.
 ## Rigorous definition
 A classification algorithm that makes a decision for each object based on a linear combination of its [[Feature|features]]. 
 ## Types

…ence/Machine Learning/Featues/Feature.md …nce/Machine Learning/Features/Feature.mdcontent/Unit 4/Artificial Intelligence/Machine Learning/Featues/Feature.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Feature.md content/Unit 4/Artificial Intelligence/Machine Learning/Featues/Feature.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Feature.md

@@ -1,4 +1,4 @@
-(also known as SVM) a [[Types of Machine Learning|supervised]] machine learning algorithm used for classification and regression tasks. 
+(also known as SVM) a [[Training with Data (Types of machine learning)#Supervised Machine Learning|supervised]] machine learning algorithm used for classification and regression tasks. 
 It is a margin-maximising [[Linear classifier|linear classifier]]. It tries to find the best boundary that separates different classes in the data. 
 
 ## Principle

…Machine Learning/Featues/Kernel Trick.md …achine Learning/Features/Kernel Trick.mdcontent/Unit 4/Artificial Intelligence/Machine Learning/Featues/Kernel Trick.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Kernel Trick.md content/Unit 4/Artificial Intelligence/Machine Learning/Featues/Kernel Trick.md renamed to content/Unit 4/Artificial Intelligence/Machine Learning/Features/Kernel Trick.md

@@ -3,9 +3,9 @@ Satisfies study design dot-point "explain, at a high level, how data-driven algo
 Data-driven algorithms, such as machine learning models, learn from data by finding and recognising patterns.
 
 Instead of being explicitly programmed with rules, algorithms 'train' on a large dataset contained with input data and, depending on their type of learning, their corresponding correct output:
-- [[Types of Machine Learning|supervised]] learning
+- [[Training with Data (Types of machine learning)#Supervised Machine Learning|supervised]] learning
 	- the algorithm is given labelled data, with each input having a correct answer. (e.g. email contents, and whether the email is spam)
-- [[Types of Machine Learning|unsupervised]] learning
+- [[Training with Data (Types of machine learning)#Unsupervised Machine Learning|unsupervised]] learning
 	- the algorithm is given unlabelled data with no correct answers. The algorithm then attempts to find hidden groupings on its own.
 - reinforcement learning
 	- the algorithm learns through trial and error

content/Unit 4/Artificial Intelligence/Machine Learning/ML algorithms/Linear classifier.md

@@ -36,7 +36,7 @@ Note: if treating $x$ and $w$ as matrices, need to transpose the first term, eg
 $$
 \text{vector dot product of w and x}=-b\text{ (constant number)}
 $$
-You may recognise this from spec as the cartesian equation for a plane/hyperplane 
+You may recognise this from Specialist Maths as the cartesian equation for a plane/hyperplane 
 ($r\cdot n=r_{0}\cdot n$).
 
 Here $r$, or the position vector, is represented by $x$.