End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In this work, we propose the Coarse-grain Fine-grain Coattention Network (CFC), a new question answering model that combines information from evidence across multiple documents. The CFC consists of a coarse-grain module that interprets documents with respect to the query then finds a relevant answer, and a fine-grain module which scores each candidate answer by comparing its occurrences across all of the documents with the query. We design these modules using hierarchies of coattention and self-attention, which learn to emphasize different parts of the input. On the Qangaroo WikiHop multi-evidence question answering task, the CFC obtains a new state-of-the-art result of 70.6% on the blind test set, outperforming the previous best by 3% accuracy despite not using pretrained contextual encoders.

A decade ago, machine learning was simply a concept but today it has changed the way we interact with technology. Devices are becoming smarter, faster and better, with Machine Learning at the helm. Thus, we have designed a comprehensive list of projects in Machine Learning course that offers a hands-on experience with ML and how to build actual projects using the Machine Learning algorithms. Furthermore, this course is a follow up to our Introduction to Machine Learning course and delves further deeper into the practical applications of Machine Learning. In this blog, we will have a look at projects divided mostly into two different levels i.e.

As much as we like writing about quadrupedal robots, it's always been a little bit tricky to see how they might be commercially useful in the near term outside of specialized circumstances like disaster response. We've seen some hints of what might be possible from Boston Dynamics, which has demonstrated construction inspection with SpotMini, but that's not necessarily a situation where a robot is significantly better than a human. In September, ANYbotics brought one of their industrial quadrupeds, ANYmal, to an offshore power distribution platform in the North Sea. It's very remote, and nothing much happens there, but it still requires a human or two to wander around checking up on stuff, a job that nobody wants. A crucial task for energy providers is the reliable and safe operation of their plants, especially when producing energy offshore.

In recent years, a rising numbers of people arrived in the European Union, traveling across the Mediterranean Sea or overland through Southeast Europe in what has been later named as the European migrant crisis. In the last 5 years, more than 16 thousands people have lost their lives in the Mediterranean sea during the crossing. The United Nations Secretary General Strategy on New Technologies is supporting the use of Artificial Intelligence (AI) and Robotics to accelerate the achievement of the 2030 Sustainable Development Agenda, which includes safe and regular migration processes among the others. In the same spirit, the central idea of this project aims at using AI technology for Search And Rescue (SAR) operations at sea. In particular, we propose an autonomous fleet of self-organizing intelligent drones that would enable the coverage of a broader area, speeding-up the search processes and finally increasing the efficiency and effectiveness of migrants rescue operations.

Assassin's Creed Odyssey is aptly named. It is an enormous, meandering journey through ancient Greece at the beginning of the Peloponnesian war as the struggle between Sparta and Athens begins to reshape the Greek world. It will shock you with its breadth and depth: the sea hides sunken ruins, the detail of temple paintings is impeccable, authentically clothed characters wander enormous cities whilst chatting in Greek, soldiers clash on roads as citizens scatter. You play a mercenary, choosing between the equally statuesque and self-assured Kassandra or Alexios. There is an element of family drama that propels the story forward in counterpart to the overarching historical drama of the setting.

Autonomous Robotics, a subsidiary of listed company Thalassa, is to collaborate with Robert Gordon University to conduct research on swarm technology of autonomous underwater vehicles in the North Sea. The work is supported by the Oil & Gas Innovation Centre. The purpose of this research is to further enhance the capability of the'flying node' system and further reduce the cost and time for ocean bottom seismic surveys. The Swarm Technology research will be performed by Dr Wai-keung Fung and Mr Adham Sabra, who are with the Communications and Autonomous Systems Group within the School of Engineering, with results are expected within 12 months. Chairman Dave Grant said: "ARL are working with RGU to research and create a practical localisation system for the flying node system which will allow the flying nodes to operate in a swarm and move from their initial seabed position to a new seabed location.

Text analytics based on supervised machine learning classifiers has shown great promise in a multitude of domains, but has yet to be applied to Seismology. We test various standard models (Naive Bayes, k-Nearest Neighbors, Support Vector Machines, and Random Forests) on a seismological corpus of 100 articles related to the topic of precursory accelerating seismicity, spanning from 1988 to 2010. This corpus was labelled in Mignan (2011) with the precursor whether explained by critical processes (i.e., cascade triggering) or by other processes (such as signature of main fault loading). We investigate rather the classification process can be automatized to help analyze larger corpora in order to better understand trends in earthquake predictability research. We find that the Naive Bayes model performs best, in agreement with the machine learning literature for the case of small datasets, with cross-validation accuracies of 86% for binary classification. For a refined multiclass classification ('non-critical process' < 'agnostic' < 'critical process assumed' < 'critical process demonstrated'), we obtain up to 78% accuracy. Prediction on a dozen of articles published since 2011 shows however a weak generalization with a F1-score of 60%, only slightly better than a random classifier, which can be explained by a change of authorship and use of different terminologies. Yet, the model shows F1-scores greater than 80% for the two multiclass extremes ('non-critical process' versus 'critical process demonstrated') while it falls to random classifier results (around 25%) for papers labelled 'agnostic' or 'critical process assumed'. Those results are encouraging in view of the small size of the corpus and of the high degree of abstraction of the labelling. Domain knowledge engineering remains essential but can be made transparent by an investigation of Naive Bayes keyword posterior probabilities.

Merging beliefs requires the plausibility of the sources of the information to be merged. They are typically assumed equally reliable when nothing suggests otherwise. A recent line of research has spun from the idea of deriving this information from the revision process itself. In particular, the history of previous revisions and previous merging examples provide information for performing subsequent merging operations. Yet, no examples or previous revisions may be available. In spite of the apparent lack of information, something can still be inferred by a try-and-check approach: a relative reliability ordering is assumed, the sources are integrated according to it and the result is compared with the original information. The final check may contradict the original ordering, like when the result of merging implies the negation of a formula coming from a source initially assumed reliable, or it implies a formula coming from a source assumed unreliable. In such cases, the reliability ordering assumed in the first place can be excluded from consideration. Such a scenario is proved real under the classifications of source reliability and definitions of belief integration considered in this article: sources divided in two, three or multiple reliability classes; integration is mostly by maximal consistent subsets but also weighted distance is considered.

For the operators of large helicopters, the principle of big data is nothing new. For years, these companies and their associated MRO operations have been collecting and analyzing vibration data from onboard health and usage monitoring systems (HUMS), looking for potential issues within an aircraft's dynamic systems as well as clues to potential maintenance problems. However, in the current era of analytics, artificial intelligence (AI) and algorithms, new uses for the data coming off the helicopters are being enabled and helping to democratize the use of systems like HUMS. "Today in the helicopter world, a lot of things are being done in the maintenance world as they would have been 40-50 years ago," says Matthieu Louvot, executive vice president for customer support and services at Airbus Helicopters. "Now is the time to digitize."

Two tiny robots have landed safely on an asteroid after a Japanese spacecraft dropped them there on Friday. The scientists behind the historic mission expressed their delight as the rovers sent back the first images from the surface of the space rock Ryugu. Dubbed MINERVA-II1, the robotic explorers are the first of their kind to be successfully landed on an asteroid. The Japanese space agency JAXA announced that both units were operational after a period of silence between the unmanned spacecraft Hayabusa-2 depositing them and connection being established with the team on Earth. "I cannot find words to express how happy I am that we were able to realise mobile exploration on the surface of an asteroid," said Hayabusa-2 project manager Dr Yuichi Tsuda.