Skip to content
UoL CS Notes

Home

This website houses notes from my studies at the University of Liverpool. If you see any errors or issues, please do open an issue on this site's GitHub.

Lecture 25

COMP105 Lectures

IO Example In this lecture we are covering an extended example on making ASCII art of a given input char. It will add chars onto the resultant output when you give them as input. As this is an example lecture I will be taking notes on key concepts, for the...

Read More

Nearest Neighbour Classifier - 2

COMP111 Lectures

$k$-Nearest Neighbour Classifier For $x$ to be classifier find $k$ nearest $x_{i_1},\ldots,x_{i_k}$ in the training data. Classify $x$ according to the majority vote of their class labels. For $k=3$: The $k$ represents the number of closest labels you are taking into account. 1: Input: training data (x0, L(x0)), ... ,...

Read More

Nearest Neighbour Classifier - 1

COMP111 Lectures

This classifier is an example of similarity based classifiers. Similarity Measures Assume that we can measure the similarity between items in the training data $\mathcal X$. For example: One could measure how similar two emails are by counting the number of words from the English dictionary they both contain and...

Read More

Logic - 7

COMP109 Lectures

Number Systems To indicate that a number of from a particular base system then use a subscript to denote this: $4268_{10}$ $1100\ 0111_2$ In a positional system you should multiply each digit by its place value: $4268_{10}=4\times 10^3+2\times 10^2+6\times 10^1 +$$\ 8\times 10^0$ Convert Decimal to Binary The rule is...

Read More

Assessment 2 - Meeting 2

COMP107 Meetings

Role Call All members were present apart from Josef. Users We started to work on the colaborative document by identifiying our key users. The users we thought of were: Families Disabled People Shopper Buisness Managers User Stories We also discussed and started work on the user stories using the template...

Read More

Relational DB Quality - 2

COMP107 Lectures

Normalisation This is the mathematical process of reducing linked tables to a normal form. Functional Dependencies This is a formal tool for analysis of relational schemas. The theory of functional dependencies allows us to describe as detect issues in precise terms. A functional dependency is constraint between two sets of...

Read More

Relational DB Quality - 1

COMP107 Lectures

Design Guidelines Semantics of Attributes Each relation should be a set of instances of a specific concept. This means that in a particular table that all attributes should be directly related. Design relation schema so that it is easy to explain its meaning. Do not combine attributes from multiple entity...

Read More

Naive Bayes Classifier - 2

COMP111 Lectures

Suppose we want to predict the class of the instance with features $(e_1,\ldots,e_n)$. We assume $E_1,\ldots,E_n$ are independent given $Y$ and estimate: \[V_y=P(Y=y)\prod^n_{i=1}P(E_i=e_i\vert Y=y)\] The $\prod$ symbol means the product of. for all $y\in \mathcal Y$ as follows: $P(Y=y)$ is estimated by the number of instance labelled with $y$ in...

Read More

Naive Bayes Classifier - 1

COMP111 Lectures

Supervised Learning of Classifiers Given: A set $\mathcal X$ of possible instances of be classified: Emails Hand-written digits Image windows A finite set $\mathcal Y$ of classes: $\{\text{spam, not spam}\}$ Training data $(x_1,L(x_1)),\ldots,(x_n,(L(x_n))\in \mathcal X \times \mathcal Y$. $L(x_1)$ is called the label of $x_i$. A class of functions $\mathcal...

Read More

Introduction to Learning

COMP111 Lectures

Learning is the process of converting experience into expertise or knowledge. For a machine the input to a learning algorithms is training data (representing experience) and the output is some expertise, which usually takes the form of another computer program that can perform some task. Types of Learning Supervised Learning...

Read More