Lighting the black box: explaining individual predictions of machine learning algorithms

Many machine learning techniques remain ''black boxes'' because, despite their high predictive performance, it is difficult to understand the role of each variable involved in the prediction task. In this thesis, we will study three methods that explain individual predictions of...

ver descrição completa

Detalhes bibliográficos
Autor: Ferrando Hernández, Pol
Formato: tesis de maestría
Fecha de publicación:2018
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/113463
Acesso em linha:https://hdl.handle.net/2117/113463
Access Level:acceso abierto
Palavra-chave:Artificial intelligence
Machine learning
Interpretability
Intel·ligència artificial
Classificació AMS::68 Computer science::68T Artificial intelligence
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial
Descrição
Resumo:Many machine learning techniques remain ''black boxes'' because, despite their high predictive performance, it is difficult to understand the role of each variable involved in the prediction task. In this thesis, we will study three methods that explain individual predictions of any model and determine what explanatory variables are most influential for each particular observation, which brings transparency to machine learning algorithms. Additionally, we will test these methods on a simple dataset for which we can assess the quality of the explanations.