Commit 5b390bf5 authored by David Peter's avatar David Peter
Browse files

Typos

parent 24f895ca
No preview for this file type
......@@ -80,7 +80,7 @@ The shape of the \gls{relu} is depicted in Figure~\ref{fig:relu}. A positive cha
\addlegendentry{$g(z) = \max\{0, z\}$}
\end{axis}
\end{tikzpicture}
\caption{ReLU activation function.}
\caption{\gls{relu} activation function.}
\label{fig:relu}
\end{figure}
......
......@@ -11,7 +11,7 @@ The term \textit{supervised} in supervised learning is attributed to the fact th
An example of a supervised classification task is object recognition on the \textit{MNIST}~\cite{Lecun1998} dataset. The \textit{MNIST} dataset is a popular dataset containing images of handwritten numbers from \num{0} to \num{9}. The goal is to assign the correct number to every input image.
An example of a supervised regression task is the house price prediction on the \textit{Boston Housing}~\cite{Harrison1978} dataset. The \textit{Boston Housing} dataset consists of descriptions of boston suburbs or towns. Every suburb or town is assigned certain features like the average number of rooms per dwelling or the per capita crime rate. The goal is to predict the price of a house given the features.
An example of a supervised regression task is the house price prediction on the \textit{Boston Housing}~\cite{Harrison1978} dataset. The \textit{Boston Housing} dataset consists of descriptions of Boston suburbs or towns. Every suburb or town is assigned certain features like the average number of rooms per dwelling or the per capita crime rate. The goal is to predict the price of a house given the features.
\paragraph{Unsupervised learning} In unsupervised learning, unlabeled data is given. An unlabeled dataset consists of a set of $N$ inputs $\mathbb{X} = \{\vm{x}_1, \dots, \vm{x}_N\}$ without corresponding targets. The goal of unsupervised learning is to find a structure in the given data. One example of unsupervised learning is clustering, where inputs with similar properties are grouped together.
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment