Tasks involving the analysis of geometric (graph- and manifold-structured) data have recently gained prominence in the machine learning community, giving birth to a rapidly developing field of geometric deep learning. In this work, we leverage graph neural networks to improve signal detection in the IceCube neutrino observatory. The IceCube detector array is modeled as a graph, where vertices are sensors and edges are a learned function of the sensors' spatial coordinates. As only a subset of IceCube's sensors is active during a given observation, we note the adaptive nature of our GNN, wherein computation is restricted to the input signal support. We demonstrate the effectiveness of our GNN architecture on a task classifying IceCube events, where it outperforms both a traditional physics-based method as well as classical 3D convolution neural networks.

In this paper, we show how unsupervised sense representations can be used to improve hypernymy extraction. We present a method for extracting disambiguated hypernymy relationships that propagates hypernyms to sets of synonyms (synsets), constructs embeddings for these sets, and establishes sense-aware relationships between matching synsets. Evaluation on two gold standard datasets for English and Russian shows that the method successfully recognizes hypernymy relationships that cannot be found with standard Hearst patterns and Wiktionary datasets for the respective languages.

WASHINGTON (WASHINGTON POST) - A new poll shows that in several countries around the world, large majorities of people believe it is most likely that robots will be doing much of the work done by humans within 50 years. The effects of this technological leap are not viewed optimistically by most, however. Instead, people largely say they think humans will struggle to find meaningful work and inequality will rise, the research found. The poll was conducted earlier this year by the Pew Research Centre in Greece, Japan, Canada, Argentina, Poland, Brazil, South Africa, Italy and Hungary. Pew also compared the responses in those countries to a poll done in the United States in 2015 that asked about automation. In general, the poll found that majorities in most countries were in agreement that robots would soon do humans' work, with only limited differences in their views of how this would affect society despite some countries being advanced economically and others still developing.

Recently, product images have gained increasing attention in clothing recommendation since the visual appearance of clothing products has a significant impact on consumers' decision. Most existing methods rely on conventional features to represent an image, such as the visual features extracted by convolutional neural networks (CNN features) and the scale-invariant feature transform algorithm (SIFT features), color histograms, and so on. Nevertheless, one important type of features, the \emph{aesthetic features}, is seldom considered. It plays a vital role in clothing recommendation since a users' decision depends largely on whether the clothing is in line with her aesthetics, however the conventional image features cannot portray this directly. To bridge this gap, we propose to introduce the aesthetic information, which is highly relevant with user preference, into clothing recommender systems. To achieve this, we first present the aesthetic features extracted by a pre-trained neural network, which is a brain-inspired deep structure trained for the aesthetic assessment task. Considering that the aesthetic preference varies significantly from user to user and by time, we then propose a new tensor factorization model to incorporate the aesthetic features in a personalized manner. We conduct extensive experiments on real-world datasets, which demonstrate that our approach can capture the aesthetic preference of users and significantly outperform several state-of-the-art recommendation methods.

Data heterogeneity hampers the effort to integrate and infer knowledge from vast heterogeneous data sources. An application case study is described, in which the objective was to semantically represent and integrate structured data from sensor devices with unstructured data in the form of local indigenous knowledge. However, the semantic representation of these heterogeneous data sources for environmental monitoring systems is not well supported yet. To combat the incompatibility issues, a dedicated semantic middleware solution is required. In this paper, we describe and evaluate a cross-domain middleware architecture that semantically integrates and generate inference from heterogeneous data sources. These use of semantic technology for predicting and forecasting complex environmental phenomenon will increase the degree of accuracy of environmental monitoring systems.

The Chart of the Week is a weekly Visual Capitalist feature on Fridays. Artificial Intelligence is transforming the way we live, and the tech giants are racing to stay ahead of the curve. AI-related funding totaled an estimated $15.2 billion in 2017, a 144% increase over the previous year. The U.S. tech industry leads with a 50% share of those investments, even with China swiftly closing the gap in terms of patents and AI research. AI itself isn't new, but boosted computing power, increased connectivity, and the sheer volume of data has paved the way for the fourth industrial revolution of AI. "The coming era will be looked back upon as the'AI era,' when AI became the defining competitive advantage for corporations, government agencies, and investment professionals," predicts David Nadler, founder of Kensho Technologies.

It's called'Aibo,' and is promoted as using artificial intelligence to respond to people looking at it, talking to it and touching it. Japanese customers have already bought over 20,000 units, and it is expected to come to the U.S. before the holiday gift-buying season – at a price nearing US$3,000. Why would anyone pay so much for a robotic dog? My ongoing research suggests part of the attraction might be explained through humanity's longstanding connection with various forms of puppets, religious icons, and other figurines, that I collectively call'dolls.' These dolls, I argue, are embedded deep in our social and religious lives.

FOR the time being, Cape Town has dodged a bullet. After months of unrelenting drought, the recent winter rains have begun to refill its parched dams. That doesn't mean things are easy. City residents are still limited to using 50 litres of water a day, scarcely enough to half-fill a bath. But at least so-called day zero, when the taps run dry and residents have to wait in line to collect survival rations of water, has been averted.

Forest loss is being driven by various factors, including commodity production, forestry, agriculture, wildfire, and urbanization. Curtis et al. used high-resolution Google Earth imagery to map and classify global forest loss since 2001. Just over a quarter of global forest loss is due to deforestation through permanent land use change for the production of commodities, including beef, soy, palm oil, and wood fiber. Despite regional differences and efforts by governments, conservationists, and corporations to stem the losses, the overall rate of commodity-driven deforestation has not declined since 2001. Global maps of forest loss depict the scale and magnitude of forest disturbance, yet companies, governments, and nongovernmental organizations need to distinguish permanent conversion (i.e., deforestation) from temporary loss from forestry or wildfire.

Abstract--Social media conversations unfold based on complex interactions between users, topics and time. While recent models have been proposed to capture network strengths between users, users' topical preferences and temporal patterns between posting and response times, interaction patterns between topics has not been studied. We argue that social media conversations naturally involve interacting rather than independent topics. Modeling such topical interaction patterns can additionally help in inference of latent variables in the data such as diffusion parents and topics of events. We propose the Hidden Markov Hawkes Process (HMHP) that incorporates topical Markov Chains within Hawkes processes to jointly model topical interactions along with useruser and user-topic patterns. We propose a Gibbs sampling algorithm for HMHP that jointly infers the network strengths, diffusion paths, the topics of the posts as well as the topictopic interactions. We show using experiments on real and semisynthetic data that HMHP is able to generalize better and recover the network strengths, topics and diffusion paths more accurately that state-of-the-art baselines. More interestingly, HMHP finds insightful interactions between topics in real tweets which no existing model is able to do. This can potentially lead to actionable insights enabling, e.g., user targeting for influence maximization. A popular area of recent research has been the study of information diffusion cascades, where information spreads over a social network when a'parent' event from one infected node influences a'child' event at neighboring node [5], [11], [19], [6], [10]. The action of propagating information between two neighboring nodes depends on various factors, such as the strength of influence between the nodes, the topical content of the parent event and the extent of interest of the child node towards that topic. Explosion of social media data has made it possible to analyze and evaluate different models that seek to explain such information cascades. However, many relevant variables such as the network influence strengths, the identity of influencing or parent event for any event, and the actual topics are typically unobserved for most social network data.