Minhas tags são as seguintes:
\documentclass{book}
\usepackage{showframe}
\begin{document}
Deep learning has transformed computer vision, natural language and speech processing in particular, and artificial intelligence in general. From a bag of semi-discordant tricks, none of which worked satisfactorily on real-life problems, artificial intelligence has become a formidable tool to solve real problems faced by industry, at scale. This is nothing short of a revolution going on under our very noses. To lead the curve of this revolution, it is imperative to understand the underlying principles and abstractions rather than simply memorizing the ``how-to'' steps of some hands-on guide. This is where mathematics comes in.
\section{First Level Head}
In this first chapter, we present an overview of deep learning. This will require us to use some concepts explained in subsequent chapters. Don't worry if there are some open questions at the end of this chapter: it is aimed at orienting your mind toward this difficult subject. As individual concepts become clearer in subsequent chapters, you should consider coming back and re-reading this chapter.
For instance, a cat's brain is often trying to choose between the following options:
\emph{run away} from the object in front of it vs.
\emph{ignore} the object in front of it vs. \emph{approach} the
object in front of it and purr. The cat's brain makes that decision
by processing sensory inputs like the perceived \emph{hardness} of
the object in front of it, the perceived \emph{sharpness} of the
object in front of it, and so on.
This is an instance of a \emph{classification} problem, where the output is one of a set of possible classes.
Some other examples of classification problems in life are as follows:
\begin{itemize}
\item \emph{Buy} vs. \emph{hold} vs. \emph{sell}
a certain stock, from inputs like the
\emph{price history of this stock} and the
\emph{change in price of the stock in recent times}
\item Object recognition (from an image):
\begin{itemize}
\item Is this a car or a giraffe?
\item Is this a human or a non-human?
\item Is this an inanimate object or a living object?
\item Face recognition---is this Tom or Dick or Mary or Einstein or Messi?
\end{itemize}
\item Action recognition from a video:
\begin{itemize}
\item Is this person running or not running?
\item Is this person picking something up or not?
\item Is this person doing something violent or not?
\end{itemize}
\item Natural language processing (NLP) from digital documents:
\begin{itemize}
\item Does this news article belong to the realm of politics or sports?
\item Does this query phrase match a particular article in the archive?
\end{itemize}
\end{itemize}
\subsection{Second Level Head}
Another instance of quantitative estimation is estimating a house's price based on inputs like current income of the house's owner, crime statistics for the neighborhood, and so on.
Machines that make such quantitative estimators are called \textit{regressors}.
\end{document}
A primeira página terminou com o textoin the archive?
É possível capturar todo e qualquer texto de final de página em um arquivo de saída separado, por exemplo:
A página 1 terminou comin the archive?
A página 2 terminou com..so and so...
Por favor, informe
Responder1
Se você executar o pdftotext no pdf gerado acima, você obterá um arquivo de texto com páginas separadas por feed de formulário (ctrl-L) que termina–
Is this person doing something violent or not?
• Natural language processing (NLP) from digital documents:
– Does this news article belong to the realm of politics or sports?
– Does this query phrase match a particular article in the archive?
^L2
0.1.1
Second Level Head
Another instance of quantitative estimation is estimating a house’s price based
on inputs like current income of the house’s owner, crime statistics for the
neighborhood, and so on. Machines that make such quantitative estimators are
called regressors.
^L
Portanto, se você remover as linhas em branco e pegar cada linha acima de um feed de formulário, obterá mais ou menos o texto solicitado:
$ sed -e '/^[ \t]*$/d' aa072.txt |grep -B1 -P "\x0C"
– Does this query phrase match a particular article in the archive?
2
--
called regressors.