Benseny, AntoniRubio Muñoz, AlbertoMarín Sánchez, Gabriel2021-06-012021-06-012020-06-22https://hdl.handle.net/2445/177854Treballs Finals de Grau de Matemàtiques, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2020, Director: Antoni Benseny i Alberto Rubio Muñoz[en] From image creation and pattern recognition to speech and text processing, the outstanding performance of neural networks in a wide variety of fields has made them a popular tool among researchers. However, the fact that we do not fully understand why their performance is so successful or how they operate converts this technology into a black-box model based on trial and error. In this work, we attempt to give deep neural networks a mathematical representation and present different examples and applications that bring light to the understanding of neural networks’ behaviour and usage.56 p.application/pdfengcc-by-nc-nd (c) Gabriel Marín Sánchez, 2020http://creativecommons.org/licenses/by-nc-nd/3.0/es/Intel·ligència artificialTreballs de fi de grauXarxes neuronals (Informàtica)Sistemes experts (Informàtica)Artificial intelligenceBachelor's thesesNeural networks (Computer science)Expert systems (Computer science)info:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/openAccess