Institution
Polytechnic University of Catalonia
Education•Barcelona, Spain•
About: Polytechnic University of Catalonia is a education organization based out in Barcelona, Spain. It is known for research contribution in the topics: Finite element method & Population. The organization has 16006 authors who have published 45325 publications receiving 949306 citations. The organization is also known as: UPC - BarcelonaTECH & Technical University of Catalonia.
Papers published on a yearly basis
Papers
More filters
•
TL;DR: A task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning, and features the possibility to control both the stability and compactness of the learned knowledge, which makes it also attractive for online learning or network compression applications.
Abstract: Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserves previous tasks' information without affecting the current task's learning. A hard attention mask is learned concurrently to every task, through stochastic gradient descent, and previous masks are exploited to condition such learning. We show that the proposed mechanism is effective for reducing catastrophic forgetting, cutting current rates by 45 to 80%. We also show that it is robust to different hyperparameter choices, and that it offers a number of monitoring capabilities. The approach features the possibility to control both the stability and compactness of the learned knowledge, which we believe makes it also attractive for online learning or network compression applications.
379 citations
••
TL;DR: In this article, the scattering of terahertz radiation on a graphene-based nano-patch antenna is numerically analyzed and the extinction cross section of the nano-antenna supported by silicon and silicon dioxide substrates of different thickness is calculated.
Abstract: The scattering of terahertz radiation on a graphene-based nano-patch antenna is numerically analyzed. The extinction cross section of the nano-antenna supported by silicon and silicon dioxide substrates of different thickness are calculated. Scattering resonances in the terahertz band are identified as Fabry–Perot resonances of surface plasmon polaritons supported by the graphene film. A strong tunability of the antenna resonances via electrostatic bias is numerically demonstrated, opening perspectives to design tunable graphene-based nano-antennas. These antennas are envisaged to enable wireless communications at the nanoscale. # 2012 Elsevier B.V. All rights reserved.
375 citations
•
28 Apr 2011
TL;DR: This paper proposes an extension to the independent cascade model that incorporates the emergence and propagation of negative opinions, and designs an efficient algorithm to compute influence in tree structures, which is nontrivial due to the negativity bias in the model.
Abstract: Influence maximization, defined by Kempe, Kleinberg, and Tardos (2003), is the problem of finding a small set of seed nodes in a social network that maximizes the spread of influence under certain influence cascade models. In this paper, we propose an extension to the independent cascade model that incorporates the emergence and propagation of negative opinions. The new model has an explicit parameter called quality factor to model the natural behavior of people turning negative to a product due to product defects. Our model incorporates negativity bias (negative opinions usually dominate over positive opinions) commonly acknowledged in the social psychology literature. The model maintains some nice properties such as submodularity, which allows a greedy approximation algorithm for maximizing positive influence within a ratio of 1-1/e. We define a quality sensitivity ratio (qs-ratio) of influence graphs and show a tight bound of T(vn/k) on the qs-ratio, where n is the number of nodes in the network and k is the number of seeds selected, which indicates that seed selection is sensitive to the quality factor for general graphs. We design an efficient algorithm to compute influence in tree structures, which is nontrivial due to the negativity bias in the model. We use this algorithm as the core to build a heuristic algorithm for influence maximization for general graphs. Through simulations, we show that our heuristic algorithm has matching influence with a standard greedy approximation algorithm while being orders of magnitude faster.
372 citations
••
TL;DR: An extensive review of recently published papers on hybrid flow shop (HFS) scheduling problems is presented and the papers are classified first according to the HFS characteristics and production limitations considered in the respective papers and then according toThe solution approach proposed.
370 citations
••
TL;DR: In this paper, the connection between the fractional Laplacian operator and a class of conformally covariant operators in conformal geometry was studied, and the connections between Caffarelli and Silvestre were established.
369 citations
Authors
Showing all 16211 results
Name | H-index | Papers | Citations |
---|---|---|---|
Frede Blaabjerg | 147 | 2161 | 112017 |
Carlos M. Duarte | 132 | 1173 | 86672 |
Ian F. Akyildiz | 117 | 612 | 99653 |
Josep M. Guerrero | 110 | 1197 | 60890 |
David S. Wishart | 108 | 523 | 76652 |
O. C. Zienkiewicz | 107 | 455 | 71204 |
Maciej Lewenstein | 104 | 931 | 47362 |
Jordi Rello | 103 | 694 | 35994 |
Anil Kumar | 99 | 2124 | 64825 |
Surendra P. Shah | 99 | 710 | 32832 |
Liang Wang | 98 | 1718 | 45600 |
Aharon Gedanken | 96 | 861 | 38974 |
María Vallet-Regí | 95 | 711 | 41641 |
Bonaventura Clotet | 94 | 784 | 39004 |
Roberto Elosua | 90 | 481 | 54019 |