Výsledky vyhledávání - "Castro Rabal, Jorge"

Autor: Castro Rabal, Jorge, Gabarró Vallès, Joaquim, Serna Iglesias, María José

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

In this post recession time it is important to measure the possibilities offered by a society in relation to investments. To do that, we consider an investment schema I= (R;R_1,...,R_n) where R is a lower bound on the desired return and the R_i's are

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::fa16d9da135cf914c60558b65c28522c
https://hdl.handle.net/2117/128507

Zobrazit plný text záznamu

Ordocoordinación: cómo organizar 700 estudiantes en un nuevo campus (y no morir en el intento)

Autor: Castro Rabal, Jorge, Farreres de la Morena, Xavier, Gabarró Vallès, Joaquim, Nivela Alós, M. Pilar Brígida, Pérez Poch, Antoni, Pino Blanco, Elvira, Rivero Almeida, José Miguel

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
RUA. Repositorio Institucional de la Universidad de Alicante
Universidad de Alicante (UA)
Recercat. Dipósit de la Recerca de Catalunya
instname

A partir del Q1 de 2017 el Departamento de CS de la UPC se ocupa de la docencia de Informática I en el nuevo campus de la EEBE. Dicha docencia ha sido singular en dos aspectos. Primero, hubo que organizarla al mismo tiempo que se impartía. Segundo,

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::908f8a4cf0c8ac56ec9b93e6bd46e925
http://hdl.handle.net/2117/121683

Zobrazit plný text záznamu

Learning probability distributions generated by finite-state machines

Autor: Castro Rabal, Jorge, Gavaldà Mestre, Ricard

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

We review methods for inference of probability distributions generated by probabilistic automata and related models for sequence generation. We focus on methods that can be proved to learn in the inference in the limit and PAC formal models. The meth

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6e96c69253a32ee55d636fb6f9254557

Zobrazit plný text záznamu

Bootstrapping and learning PDFA in data streams

Autor: Balle Pigem, Borja de, Castro Rabal, Jorge, Gavaldà Mestre, Ricard

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

Best Student Paper ICGI 2012 Markovian models with hidden state are widely-used formalisms for modeling sequential phenomena. Learnability of these models has been well studied when the sample is given in batch mode, and algorithms with PAC-like lear

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::aec8f5a5f7d67c1e92e0b884bf5e932f
http://hdl.handle.net/2117/17434

Zobrazit plný text záznamu

On the query complexity of quantum learners

Autor: Castro Rabal, Jorge|||0000-0002-1390-1313

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

This paper introduces a framework for quantum exact learning via queries, the so-called quantum protocol. It is shown that usual protocols in the classical learning setting have quantum counterparts. A combinatorial notion, the general halving dimens

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::1ba741b78d2da392240917b54ce23f38
https://hdl.handle.net/2117/84843

Zobrazit plný text záznamu

The Consistency dimension and distribution-dependent learning from queries

Autor: Balcázar Navarro, José Luis, Castro Rabal, Jorge, Guijarro Guillem, David

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

We prove a new combinatorial characterization of polynomial learnability from equivalence queries, and state some of its consequences relating the learnability of a class with the learnability via equivalence and membership queries of its subclasses

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::531dd37907f723a5fa430f5257e1af87
http://hdl.handle.net/2117/95948

Zobrazit plný text záznamu

A New abstract combinatorial dimension for exact learning via queries

Autor: Balcázar Navarro, José Luis, Castro Rabal, Jorge, Guijarro Guillem, David

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

We introduce an abstract model of exact learning via queries that can be instantiated to all the query learning models currently in use, while being closer to them than previous unificatory attempts. We present a characterization of those Boolean fun

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::6fd97a8c2e477e2d010fc1ed92f7d23f
http://hdl.handle.net/2117/95865

Zobrazit plný text záznamu

The Consistency dimension and distribution-dependent learning from queries: (extended abstract with appendices)

Autor: Balcázar Navarro, José Luis, Castro Rabal, Jorge, Guijarro Guillem, David, Simon, Hans-Ulrich

Publikováno v: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Recercat. Dipósit de la Recerca de Catalunya
instname

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::9b024a2a26d1d99941f7452904f21514
http://hdl.handle.net/2117/93088

Zobrazit plný text záznamu

Learning nearly monotone k-term DNF

Autor: Castro Rabal, Jorge|||0000-0002-1390-1313, Guijarro Guillem, David, Lavín Puente, Víctor Angel

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

This note studies the learnability of the class k-term DNF with a bounded number of negations per term. We study the case of learning with membership queries alone, and give tight upper and lower bounds on the number of negations that makes the learn

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::86cd995e5dbc9fd62a6f523a991aa8f4
https://hdl.handle.net/2117/83098

Zobrazit plný text záznamu

Simple PAC learning of simple decision lists

Autor: Castro Rabal, Jorge|||0000-0002-1390-1313, Balcázar Navarro, José Luis|||0000-0003-4248-4528

Publikováno v: Recercat. Dipósit de la Recerca de Catalunya
instname
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

We prove that log n-decision lists - the class of decision lists such that all their terms have low Kolmogorov complexity - are learnable in the simple PAC learning model. The proof is based on a transformation from an algorithm based on equivalence

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::518a8a72a1200d025b691325c6652275
https://hdl.handle.net/2117/82442

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání