Polytechnic University of Catalonia

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.

Overcoming catastrophic forgetting with hard attention to the task

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.

Graphene-based nano-patch antenna for terahertz radiation

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.

Influence maximization in social Networks when negative opinions may emerge and propagate

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.