While microscopic analysis of histopathological slides is generally considered as the gold standard method for performing cancer diagnosis and grading, the current method for analysis is extremely time consuming and labour intensive as it requires pathologists to visually inspect tissue samples in a detailed fashion for the presence of cancer. As such, there has been significant recent interest in computer aided diagnosis systems for analysing histopathological slides for cancer grading to aid pathologists to perform cancer diagnosis and grading in a more efficient, accurate, and consistent manner. In this work, we investigate and explore a deep triple-stream residual network (TriResNet) architecture for the purpose of tile-level histopathology grading, which is the critical first step to computer-aided whole-slide histopathology grading. In particular, the design mentality behind the proposed TriResNet network architecture is to facilitate for the learning of a more diverse set of quantitative features to better characterize the complex tissue characteristics found in histopathology samples. Experimental results on two widely-used computer-aided histopathology benchmark datasets (CAMELYON16 dataset and Invasive Ductal Carcinoma (IDC) dataset) demonstrated that the proposed TriResNet network architecture was able to achieve noticeably improved accuracies when compared with two other state-of-the-art deep convolutional neural network architectures. Based on these promising results, the hope is that the proposed TriResNet network architecture could become a useful tool to aiding pathologists increase the consistency, speed, and accuracy of the histopathology grading process.

Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols. Despite its simplicity, such approach yields the number of parameters that grows linearly with the vocabulary size and can lead to overfitting. In this work, we propose a much more compact K-way D-dimensional discrete encoding scheme to replace the "one-hot" encoding. In the proposed "KD encoding", each symbol is represented by a $D$-dimensional code with a cardinality of $K$, and the final symbol embedding vector is generated by composing the code embedding vectors. To end-to-end learn semantically meaningful codes, we derive a relaxed discrete optimization approach based on stochastic gradient descent, which can be generally applied to any differentiable computational graph with an embedding layer. In our experiments with various applications from natural language processing to graph convolutional networks, the total size of the embedding layer can be reduced up to 98\% while achieving similar or better performance.

Much of the literature on suboptimal, polynomial-time algorithms for multi-agent path finding focuses on undirected graphs, where motion is permitted in both directions along a graph edge. Despite this, traveling on directed graphs is relevant in navigation domains, such as path finding in games, and asymmetric communication networks.We consider multi-agent path finding on strongly biconnected directed graphs. We show that all instances with at least two unoccupied positions have a solution, except for a particular, degenerate subclass where the graph has a cyclic shape. We present diBOX, an algorithm for multi-agent path finding on strongly biconnected directed graphs. diBOX runs in polynomial time, computes suboptimal solutions and is complete for instances on strongly biconnected digraphs with at least two unoccupied positions. We theoretically analyze properties of the algorithm and properties of strongly biconnected directed graphs that are relevant to our approach. We perform a detailed empirical analysis of diBOX, showing a good scalability. To our knowledge, our work is the first study of multi-agent path finding focused on directed graphs.

We consider fractional hedonic games, a subclass of coalition formation games that can be succinctly modeled by means of a graph in which nodes represent agents and edge weights the degree of preference of the corresponding endpoints. The happiness or utility of an agent for being in a coalition is the average value she ascribes to its members. We adopt Nash stable outcomes as the target solution concept; that is we focus on states in which no agent can improve her utility by unilaterally changing her own group. We provide existence, efficiency and complexity results for games played on both general and specific graph topologies. As to the efficiency results, we mainly study the quality of the best Nash stable outcome and refer to the ratio between the social welfare of an optimal coalition structure and the one of such an equilibrium as to the price of stability. In this respect, we remark that a best Nash stable outcome has a natural meaning of stability, since it is the optimal solution among the ones which can be accepted by selfish agents. We provide upper and lower bounds on the price of stability for different topologies, both in case of weighted and unweighted edges. Beside the results for general graphs, we give refined bounds for various specific cases, such as triangle-free, bipartite graphs and tree graphs. For these families, we also show how to efficiently compute Nash stable outcomes with provable good social welfare.

The uses of machine learning - the ability for computers to learn without being explicitly programmed - is a vast growing trend, not only in academia but in the industry as well. With the ever-growing amount of data available, the easy to use programming packages, successful implementations of state-of-the-art machine learning solutions is now at the fingertips of everyone. ICES will host the first workshop to better understand where machine learning and/or deep learning may be of greatest benefit within its existing fisheries science processes, such as survey and data collection, data handling, analysis and assessment, and review and advice. Participants will be sought from as wide a community as is possible. Scientists with skills in surveying, stock assessment, social aspects, and experience in ICES advisory processe, as well as interdisciplinary scientists are encouraged to participate.

"Those three make a lot of sense," says Charles Moldow, a general partner at Foundation Capital, a venture-capital firm in Palo Alto, Calif. "These are the areas we are most focused on," he says. Artificial intelligence has benefited from advances in processing power and analysis that are opening myriad new ways to create products. Meanwhile, growing attention to cryptocurrencies has helped persuade a crop of highly skilled entrepreneurs to work on putting the underlying blockchain technology to various uses. As for the third: "Cybersecurity should be a perennial anchor on the list," Mr. Moldow says.

He has more than 20 years of experience in the telecommunications, IT Infrastructure, and security industries. Previously he held positions as general manager data center division and senior vice president core technology at Trend Micro. Before that John was senior director of product management at Lucent Technologies. He has lived and worked in Europe, Asia, and the United States. John graduated with a bachelor of telecommunications engineering degree from Plymouth University, United Kingdom.

Today, the European Commission hosted a high-level meeting with 12 representatives from philosophical and non-confessional organisations from across Europe, as part of the regular dialogue with churches, religions, philosophical and non-confessional organisations foreseen by Article 17 of the Lisbon Treaty. This ninth annual high-level meeting discussed the topic "Artificial Intelligence: addressing ethical and social challenges". First Vice-President Frans Timmermans, responsible for the Article 17 Dialogue said: "Our societies are in the midst of an unprecedented digital revolution which will impact every person living on the planet. This revolution brings new promises, and new risks of disruption. We have seen recently that the digital world moved faster than the ethical discussion about what could and should be allowed online. We need to be in control of this transformation, and make sure that it is used to foster our values and defend our social model".

NASA's Curiosity Rover is living its best life through a massive dust storm on Mars, while Opportunity has been forced to hunker down. An artist's conception of a Martian dust storm, which might also crackle with electricity. A giant dust storm has enveloped the entire planet of Mars, with dust clouds reaching up to 40 miles high, NASA announced Wednesday. The dust storm has silenced NASA's solar-powered rover Opportunity since last week, by obscuring the sun. The robot rover has gone to sleep because its solar panels are unable to provide or recharge its batteries.

Amazon is increasingly claiming territory once held exclusively by department stores - and it's doing so again, essentially placing a dressing room in your house. The retail giant has officially launched service for Prime members that allows them to try on the latest styles before they buy at no upfront charge. Customers have seven days to decide what they like and only pay for what they keep. Amazon announced Tuesday, June 20, 2017, that it's testing a new service for its Prime members that lets customers try on the latest styles before they buy at no upfront charge, take seven days to decide and only pay for what they keep Shipments arrive in a re-sealable box with a pre-paid label for returns. The company had been gradually rolling out the service to Prime members in the US over the course of the year.