Rutgers University

About: Rutgers University is a education organization based out in New Brunswick, New Jersey, United States. It is known for research contribution in the topics: Population & Poison control. The organization has 68736 authors who have published 159418 publications receiving 6713860 citations. The organization is also known as: Rutgers, The State University of New Jersey & Rutgers.

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting.

Abstract: Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a $ProbSparse$ self-attention mechanism, which achieves $O(L \log L)$ in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.

Reward, Motivation, and Emotion Systems Associated With Early-Stage Intense Romantic Love

Abstract: Early-stage romantic love can induce euphoria, is a cross-cultural phenomenon, and is possibly a developed form of a mammalian drive to pursue preferred mates. It has an important influence on social behaviors that have reproductive and genetic consequences. To determine which reward and motivation systems may be involved, we used functional magnetic resonance imaging and studied 10 women and 7 men who were intensely "in love" from 1 to 17 mo. Participants alternately viewed a photograph of their beloved and a photograph of a familiar individual, interspersed with a distraction-attention task. Group activation specific to the beloved under the two control conditions occurred in dopamine-rich areas associated with mammalian reward and motivation, namely the right ventral tegmental area and the right postero-dorsal body and medial caudate nucleus. Activation in the left ventral tegmental area was correlated with facial attractiveness scores. Activation in the right anteromedial caudate was correlated with questionnaire scores that quantified intensity of romantic passion. In the left insula-putamen-globus pallidus, activation correlated with trait affect intensity. The results suggest that romantic love uses subcortical reward and motivation systems to focus on a specific individual, that limbic cortical regions process individual emotion factors, and that there is localization heterogeneity for reward functions in the human brain.

Understanding of Internal Clustering Validation Measures

Abstract: Clustering validation has long been recognized as one of the vital issues essential to the success of clustering applications. In general, clustering validation can be categorized into two classes, external clustering validation and internal clustering validation. In this paper, we focus on internal clustering validation and present a detailed study of 11 widely used internal clustering validation measures for crisp clustering. From five conventional aspects of clustering, we investigate their validation properties. Experiment results show that S\_Dbw is the only internal validation measure which performs well in all five aspects, while other measures have certain limitations in different application scenarios.

Don't judge species on their origins

Abstract: Conservationists should assess organisms on environmental impact rather than on whether they are natives, argue Mark Davis and 18 other ecologists.