Afholdte arrangementer
Hvem er online
Dansk
EnglishPedro Cano på European Workshop on Challanges in Modern Massive Data Sets, DTU
Nye måder at analysere store mængder dataSom medlem i Netværk for Dansk Lydteknologi får du lejlighed til at høre Pedro Canos foredrag under workshoppen i Glassalen på DTU, samt lægge øre til de øvrige talere under Temaet "Social Computing" som finder sted lørdag eftermiddag. Deltagelse er gratis for eftermiddagens program men inkluderer ikke registrering til andre dele af EMMDS workshoppen.Program> 13":"30 - 14":"30 Pedro Cano Music recommendation systems":" A complex networks perspective > 14":"30 - 15":"05 Joaquin Quiñonero Candela Probabilistic machine learning in computational advertising > 15":"25 - 16":"00 Mark Herbster Resistive geometry for graph-based transduction > 16":"00 - 16":"35 Sune Lehmann Connections matter. Communities of links in complex networks > 16":"35 - 17":"10 Lars Kai Hansen TBA Læs mere om konferencen her Abstract til Pedro Canos foredragNowadays it is possible to access millions of music tracks. In order to ease users to search and discover the music, a number of recommendation systems have been proposed. We analyze the topology of several commercial recommendation systems from a Complex networks perspective. We observe structural properties that provide some hints on searchability and behaviour of music recommendation systems. For example, is the Long Tail truly exploited? How much of the network structure is due to actual musical similarity and how much to other network growth processes?. The properties derived allows us to compare different recommendation approaches":" Expert-based, Collaborative filtering and Content-based. Finally, we provide possible optimizations when designing music information systems. BioDr Pedro CanoPedro is a founder of BMAT, and currently the CTO.PhD in Computer Science and Communication, Telecommunication Engineer and a post-degree of EOI Business School. Author of a book on audio fingerprinting and semantic audio and more than 45 publications in international journals and conferences as well as has 5 patents in the audio and music computing area.Previously researcher at the MTG. Assistant professor in the Department of Technology at UPF. Recipient of an ICREA Junior scholarship and a Entrepreneur XXI Award.
Pedro Cano på European Workshop on Challanges in Modern Massive Data Sets, DTU
Nye måder at analysere store mængder dataSom medlem i Netværk for Dansk Lydteknologi får du lejlighed til at høre Pedro Canos foredrag under workshoppen i Glassalen på DTU, samt lægge øre til de øvrige talere under Temaet "Social Computing" som finder sted lørdag eftermiddag. Deltagelse er gratis for eftermiddagens program men inkluderer ikke registrering til andre dele af EMMDS workshoppen.Program> 13":"30 - 14":"30 Pedro Cano Music recommendation systems":" A complex networks perspective > 14":"30 - 15":"05 Joaquin Quiñonero Candela Probabilistic machine learning in computational advertising > 15":"25 - 16":"00 Mark Herbster Resistive geometry for graph-based transduction > 16":"00 - 16":"35 Sune Lehmann Connections matter. Communities of links in complex networks > 16":"35 - 17":"10 Lars Kai Hansen TBA Læs mere om konferencen her Abstract til Pedro Canos foredragNowadays it is possible to access millions of music tracks. In order to ease users to search and discover the music, a number of recommendation systems have been proposed. We analyze the topology of several commercial recommendation systems from a Complex networks perspective. We observe structural properties that provide some hints on searchability and behaviour of music recommendation systems. For example, is the Long Tail truly exploited? How much of the network structure is due to actual musical similarity and how much to other network growth processes?. The properties derived allows us to compare different recommendation approaches":" Expert-based, Collaborative filtering and Content-based. Finally, we provide possible optimizations when designing music information systems. BioDr Pedro CanoPedro is a founder of BMAT, and currently the CTO.PhD in Computer Science and Communication, Telecommunication Engineer and a post-degree of EOI Business School. Author of a book on audio fingerprinting and semantic audio and more than 45 publications in international journals and conferences as well as has 5 patents in the audio and music computing area.Previously researcher at the MTG. Assistant professor in the Department of Technology at UPF. Recipient of an ICREA Junior scholarship and a Entrepreneur XXI Award.
