Machine Learning or Artificial Intelligence algorithms have gained considerable scrutiny in recent times owing to their propensity towards imitating and amplifying existing prejudices in society. This has led to a niche but growing body of work that identifies and attempts to fix these biases. A first step towards making these algorithms more fair is designing metrics that measure unfairness. Most existing work in this field deals with either a binary view of fairness (protected vs. unprotected groups) or politically defined categories (race or gender). Such categorization misses the important nuance of intersectionality - biases can often be amplified in subgroups that combine membership from different categories, especially if such a subgroup is particularly underrepresented in historical platforms of opportunity. In this paper, we discuss why fairness metrics need to be looked at under the lens of intersectionality, identify existing work in intersectional fairness, suggest a simple worst case comparison method to expand the definitions of existing group fairness metrics to incorporate intersectionality, and finally conclude with the social, legal and political framework to handle intersectional fairness in the modern context.

Interest has been rising lately towards modeling time-evolving knowledge graphs (KGs). Recently, graph representation learning approaches have become the dominant paradigm for link prediction on temporal KGs. However, the embeddingbased approaches largely operate in a black-box fashion, lacking the ability to judge the results' reliability. This paper provides a future link forecasting framework that reasons over query-relevant subgraphs of temporal KGs and jointly models the graph structures and the temporal context information. Especially, we propose a temporal relational attention mechanism and a novel reverse representation update scheme to guide the extraction of an enclosing subgraph around the query. The subgraph is expanded by an iterative sampling of temporal neighbors and attention propagation. As a result, our approach provides humanunderstandable arguments for the prediction. We evaluate our model on four benchmark temporal knowledge graphs for the link forecasting task. While being more explainable, our model also obtains a relative improvement of up to 17.7 % on MRR compared to the previous best KG forecasting methods. We also conduct a survey with 53 respondents, and the results show that the reasoning arguments extracted by the model for link forecasting are aligned with human understanding. Reasoning, a process of inferring new knowledge from available facts, has long been considered to be an essential subject in artificial intelligence (AI). Recently, the KGaugmented reasoning process has been studied in (Das et al., 2017; Ren et al., 2020), where knowledge graphs store factual information in form of triples (s, p, o), e.g. In particular, s (subject) and o (object) are expressed as nodes in knowledge graphs and p (predicate) as an edge type. Most knowledge graph models assume that the underlying graph is static. However, in the real world, facts and knowledge change with time, which can be treated as time-dependent multi-relational data. To accommodate time-evolving multi-relational data, temporal KGs have been introduced (Boschee et al., 2015), where temporal events are represented as a quadruple by extending the static triplet with timestamps describing when these events occurred, i.e. (Barack Obama, inaugurated, as president of the US, 2009/01/20).

There have been a number of recent proposals to enhance the performance of machine learning strategies for collider physics by combining many distinct events into a single ensemble feature. To evaluate the efficacy of these proposals, we study the connection between single-event classifiers and multi-event classifiers under the assumption that collider events are independent and identically distributed (IID). We show how one can build optimal multi-event classifiers from single-event classifiers, and we also show how to construct multi-event classifiers such that they produce optimal single-event classifiers. This is illustrated for a Gaussian example as well as for classification tasks relevant for searches and measurements at the Large Hadron Collider. We extend our discussion to regression tasks by showing how they can be phrased in terms of parametrized classifiers. Empirically, we find that training a single-event (per-instance) classifier is more effective than training a multi-event (per-ensemble) classifier, as least for the cases we studied, and we relate this fact to properties of the loss function gradient in the two cases. While we did not identify a clear benefit from using multi-event classifiers in the collider context, we speculate on the potential value of these methods in cases involving only approximate independence, as relevant for jet substructure studies.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. When the Navy is ready to deploy a new 60kw ship-fired laser weapon from a destroyer later this year, maritime attack strategy and tactics will enter new dimensions of massive warfare on the open seas. Later this year, the Navy reports, the emerging High-Energy Laser with Optical-dazzler and Surveillance (HELIOS) will arm an Arleigh Burke Flight IIA DDG 51 destroyer, following additional land and ocean testing and assessments. This means that Navy destroyers will operate with the ability to incinerate enemy drones with great precision at the speed of light, stunning, burning or simply disabling them.

The US Army just took a giant step toward developing killer robots that can see and identify faces in the dark. DEVCOM, the US Army's corporate research department, last week published a pre-print paper documenting the development of an image database for training AI to perform facial recognition using thermal images. Why this matters: Robots can use night vision optics to effectively see in the dark, but to date there's been no method by which they can be trained to identify surveillance targets using only thermal imagery. This database, made up of hundreds of thousands of images consisting of regular light pictures of people and their corresponding thermal images, aims to change that. How it works: Much like any other facial recognition system, an AI would be trained to categorize images using a specific number of parameters.

On Wednesday, I hosted a discussion with former secretary of defense Ashton Carter, who is now the director of the Belfer Center for Science and International Affairs at the Harvard Kennedy School. The conversation was part of WIRED's CES programming, which tackled the biggest trends that will shape 2021, from medicine to autonomous driving to defense. We took questions from viewers in real time. The conversation has been lightly edited for clarity. Nicholas Thompson: You've had an incredible 35-year career in the US government and in the private sector, working for Republicans and Democrats, always trying to identify what the most important issue of our time is, the smartest solutions to it, and the fairest ways to think about it.

Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.

This study develops a neural network-based approach for emulating high-resolution modeled precipitation data with comparable statistical properties but at greatly reduced computational cost. The key idea is to use combination of low- and high- resolution simulations to train a neural network to map from the former to the latter. Specifically, we define two types of CNNs, one that stacks variables directly and one that encodes each variable before stacking, and we train each CNN type both with a conventional loss function, such as mean square error (MSE), and with a conditional generative adversarial network (CGAN), for a total of four CNN variants. We compare the four new CNN-derived high-resolution precipitation results with precipitation generated from original high resolution simulations, a bilinear interpolater and the state-of-the-art CNN-based super-resolution (SR) technique. Results show that the SR technique produces results similar to those of the bilinear interpolator with smoother spatial and temporal distributions and smaller data variabilities and extremes than the original high resolution simulations. While the new CNNs trained by MSE generate better results over some regions than the interpolator and SR technique do, their predictions are still not as close as the original high resolution simulations. The CNNs trained by CGAN generate more realistic and physically reasonable results, better capturing not only data variability in time and space but also extremes such as intense and long-lasting storms. The new proposed CNN-based downscaling approach can downscale precipitation from 50~km to 12~km in 14~min for 30~years once the network is trained (training takes 4~hours using 1~GPU), while the conventional dynamical downscaling would take 1~month using 600 CPU cores to generate simulations at the resolution of 12~km over contiguous United States.

Conspiracy theories, or in general seriously distorted beliefs, are widespread. How and why are they formed in the brain is still more a matter of speculation rather than science. In this paper one plausible mechanisms is investigated: rapid freezing of high neuroplasticity (RFHN). Emotional arousal increases neuroplasticity and leads to creation of new pathways spreading neural activation. Using the language of neurodynamics a meme is defined as quasi-stable associative memory attractor state. Depending on the temporal characteristics of the incoming information and the plasticity of the network, memory may self-organize creating memes with large attractor basins, linking many unrelated input patterns. Memes with fake rich associations distort relations between memory states. Simulations of various neural network models trained with competitive Hebbian learning (CHL) on stationary and non-stationary data lead to the same conclusion: short learning with high plasticity followed by rapid decrease of plasticity leads to memes with large attraction basins, distorting input pattern representations in associative memory. Such system-level models may be used to understand creation of distorted beliefs and formation of conspiracy memes, understood as strong attractor states of the neurodynamics.

Farms and other agricultural operations in certain rural areas in the US can now use robotic drones to take images of or gather data on their crops. The FAA has approved Massachusetts-based American Robotics' request to be able to deploy automated drones without human pilots and spotters on site. As The Wall Street Journal notes, commercial drone flights typically require the physical presence of licensed pilots making them a costly undertaking. AR's machine eliminates the need for on-site personnel, though each automated flight will still need to be overseen by a remote human pilot. According to the relevant documents (via The Verge) the FAA has uploaded on its website, the pilot "who is not co-located with the aircraft" will have to conduct pre-flight safety checks to ensure the drone is in working condition.