Roland Szabo edited Introduction.tex  almost 10 years ago

Commit id: 0b565baa32cb7eaea4c808cdebc62fdb3f72617a

deletions | additions      

       

The deep part of the name comes from the fact that instead of having a single layer that receives the input data and outputs the desired result, we have a series of layers that process data received from the previous layer, extracting higher and higher levels of features. Only the last layer is used to obtain the result, after the data has been transformed and compressed.   Deep neural networks have been succesfully used by various research groups. \cite{Dahl} Dahl et al.  from Microsoft presented a paper about using deep neural nets for speech recogntion. recogntion \cite{Dahl}.  The following year, \cite{Le} Quoc et al.  from Google developed a system that, from 10 million YouTube thumbnails, learned by itself to recognize human faces (and 22.000 other categories of objects). objects) \cite{Le}.