000070412 001__ 70412 000070412 005__ 20180517143106.0 000070412 037__ $$aTAZ-TFG-2018-517 000070412 041__ $$aeng 000070412 1001_ $$aYus López, Diego 000070412 24200 $$aMachine Learning: Binary Non-negative Matrix Factorization 000070412 24500 $$aMachine Learning: Binary Non-negative Matrix Factorization 000070412 260__ $$aZaragoza$$bUniversidad de Zaragoza$$c2015 000070412 506__ $$aby-nc-sa$$bCreative Commons$$c3.0$$uhttp://creativecommons.org/licenses/by-nc-sa/3.0/ 000070412 520__ $$aThis bachelor thesis theoretically derives and implements an unsupervised probabilistic generative model called Binary Non-Negative Matrix Factorization. It is a simplification of the standard Non-Negative Matrix Factorization where the factorization into two matrices is restricted to one of them having only binary components instead of continuous components. This simplifies the computation making it exactly solvable while keeping most of the learning capabilities and connects the algorithm to a modified version of Binary Sparse Coding. The learning phase of the model is performed using the EM algorithm, an iterative method that maximizes the likelihood function with respect to the parameters to be learned in a two-step process. The model is tested on artificial data and it is shown to learn the hidden parameters on these simple data although it fails to work properly when applied to real data. 000070412 521__ $$aGraduado en Física 000070412 540__ $$aDerechos regulados por licencia Creative Commons 000070412 700__ $$aLücke, Jörg$$edir. 000070412 7102_ $$aUniversidad de Zaragoza$$b $$c 000070412 8560_ $$f649559@celes.unizar.es 000070412 8564_ $$s650650$$uhttps://zaguan.unizar.es/record/70412/files/TAZ-TFG-2018-517.pdf$$yMemoria (eng) 000070412 909CO $$ooai:zaguan.unizar.es:70412$$pdriver$$ptrabajos-fin-grado 000070412 950__ $$a 000070412 951__ $$adeposita:2018-05-17 000070412 980__ $$aTAZ$$bTFG$$cCIEN 000070412 999__ $$a20180515195735.CREATION_DATE