Tilburg University

About: Tilburg University is a education organization based out in Tilburg, Noord-Brabant, Netherlands. It is known for research contribution in the topics: Population & Context (language use). The organization has 5550 authors who have published 22330 publications receiving 791335 citations.

A review on the long short-term memory model

Abstract: Long short-term memory (LSTM) has transformed both machine learning and neurocomputing fields. According to several online sources, this model has improved Google’s speech recognition, greatly improved machine translations on Google Translate, and the answers of Amazon’s Alexa. This neural system is also employed by Facebook, reaching over 4 billion LSTM-based translations per day as of 2017. Interestingly, recurrent neural networks had shown a rather discrete performance until LSTM showed up. One reason for the success of this recurrent network lies in its ability to handle the exploding/vanishing gradient problem, which stands as a difficult issue to be circumvented when training recurrent or very deep neural networks. In this paper, we present a comprehensive review that covers LSTM’s formulation and training, relevant applications reported in the literature and code resources implementing this model for a toy example.

Multiculturalism and acculturation: views of Dutch and Turkish–Dutch

Abstract: The psychological component of immigration in the Netherlands was studied by comparing views on multiculturalism and acculturation orientation of Turkish migrants between Dutch majority (N=1565) and Turkish-Dutch minority (N=185) members. Multiculturalism was measured with an adaptation of the Multicultural Ideology Scale (Berry & Kalin, 1995); acculturation orientation was investigated in different domains of life. The results revealed that Dutch on average had a neutral attitude towards multiculturalism in the Netherlands while Turkish-Dutch showed a more positive attitude. Regarding the acculturation strategies, Dutch adults preferred assimilation above integration of Turkish migrants in all life domains. Turkish-Dutch adults made a distinction in public and private domains: integration was preferred in public domains, and separation in private domains. In public domains both cultural groups agreed that Turkish migrants should adapt to the Dutch culture. In private domains there was no agreement at all in the views of Dutch and Turkish-Dutch. These results suggest that the views on acculturation and multiculturalism differ substantially for majority and minority group members. Implications are discussed.

Polynomial Algorithms for Perfect Graphs

Abstract: We show that the weighted versions of the stable set problem, the clique problem, the coloring problem and the clique covering problem are solvable in polynomial time for perfect graphs. Our algorithms are based on the ellipsoid method and a polynomial time separation algorithm for a certain class of positive semidefinite matrices related to Lovasz's bound θ(G) on the Shannon capacity of a graph. We show that θG) can be computed in polynomial time for all graphs G and also give a new characterization of perfect graphs in terms of this number θ(G). In addition we prove that the problem of verifying that a graph is imperfect is in NP. Moreover, we show that the computation of the stability number and the fractional stability number of a graph are unrelated with respect to hardness (if P ≠NP).

Dynamics of multiple-goal pursuit.

Abstract: The authors propose and test a model of multiple-goal pursuit that specifies how individuals allocate effort among multiple goals over time. The model predicts that whether individuals decide to step up effort, coast, abandon the current goal, or switch to pursue another goal is determined jointly by the emotions that flow from prior goal progress and the proximity to future goal attainment, and proximally determined by changes in expectancies about goal attainment. Results from a longitudinal diary study and 2 experiments show that positive and negative goal-related emotions can have diametrically opposing effects on goal-directed behavior, depending on the individual's proximity to goal attainment. The findings resolve contrasting predictions about the influence of positive and negative emotions in volitional behavior, critically amend the goal gradient hypothesis, and provide new insights into the dynamics and determinants of multiple-goal pursuit.