Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Campos Camúñez, Víctor"'
Autor:
Campos Camúñez, Víctor
Publikováno v:
TDX (Tesis Doctorals en Xarxa)
TDR. Tesis Doctorales en Red
instname
TDR: Tesis Doctorales en Red
CBUC, CESCA
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
TDR. Tesis Doctorales en Red
instname
TDR: Tesis Doctorales en Red
CBUC, CESCA
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Deep learning has revolutionized the field of artificial intelligence in the past decade. Although the development of these techniques spans over several years, the recent advent of deep learning is explained by an increased availability of data and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::54bd5ab2264b95464ef4a1e198c04916
http://hdl.handle.net/10803/670372
http://hdl.handle.net/10803/670372
Autor:
Campos Camúñez, Víctor, Trott, Alex, Xiong, Caiming, Socher, Richard, Giró Nieto, Xavier|||0000-0002-9935-5332, Torres Viñals, Jordi|||0000-0003-1963-7418
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Universitat Politècnica de Catalunya (UPC)
Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery and informat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d0fe7e612f77d17d93dfdc5b79bdf591
https://hdl.handle.net/2117/332308
https://hdl.handle.net/2117/332308
Autor:
Campos Camúñez, Víctor
Publikováno v:
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname
Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and dificulty in capturing long term depende
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::4f4d898e09b3654ee6820e1c5c60af24
http://hdl.handle.net/2117/108676
http://hdl.handle.net/2117/108676
Autor:
Campos Camúñez, Víctor
Publikováno v:
Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Investigate the potential of deep learning techniques in the field of computer vision applied to affective computing. Visual media are powerful means of expressing emotions and sentiments. The constant generation of new content in social networks hig
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::832ef0d4d31edc4c5fa15d22e99a32d8
http://hdl.handle.net/2117/78383
http://hdl.handle.net/2117/78383