|
Título:
|
Quantum speedup for active learning agents
|
|
Autores:
|
Davide Paparo, Giuseppe ;
Dunjko, Vedran ;
Makmal, Adi ;
Martín-Delgado Alcántara, Miguel Ángel ;
Briegel, Hans J.
|
|
Tipo de documento:
|
texto impreso
|
|
Editorial:
|
American Physical Society (APS), 2014-06-08
|
|
Dimensiones:
|
application/pdf
|
|
Nota general:
|
info:eu-repo/semantics/openAccess
|
|
Idiomas:
|
|
|
Palabras clave:
|
Estado = Publicado
,
Materia = Ciencias: Física: Física-Modelos matemáticos
,
Tipo = Artículo
|
|
Resumen:
|
Can quantum mechanics help us build intelligent learning agents? A defining signature of intelligent behavior is the capacity to learn from experience. However, a major bottleneck for agents to learn in reallife situations is the size and complexity of the corresponding task environment. Even in a moderately realistic environment, it may simply take too long to rationally respond to a given situation. If the environment is impatient, allowing only a certain time for a response, an agent may then be unable to cope with the situation and to learn at all. Here, we show that quantum physics can help and provide a quadratic speedup for active learning as a genuine problem of artificial intelligence. This result will be particularly relevant for applications involving complex task environments.
|
|
En línea:
|
https://eprints.ucm.es/id/eprint/47323/1/Mart%C3%ADn%20Delgado%20Alc%C3%A1ntara%20M%C3%81%2005%20LIBRE.pdf
|
