Class imbalance has been one of the major challenges for medical image segmentation. The model cascade (MC) strategy significantly alleviates class imbalance issue. In spite of its outstanding performance, this method leads to an undesired system complexity and meanwhile ignores the relevance among the models. To handle these flaws of MC, we propose in this paper a light-weight deep model, i.e., the One-pass Multi-task Network (OM-Net) to solve class imbalance better than MC and require only one-pass computation for brain tumor segmentation. First, OM-Net integrates the separate segmentation tasks into one deep model. Second, to optimize OM-Net more effectively, we take advantage of the correlation among tasks to design an online training data transfer strategy and a curriculum learning-based training strategy. Third, we further propose to share prediction results between tasks, which enables us to design a cross-task guided attention (CGA) module. With the guidance of prediction results provided by the previous task, CGA can adaptively recalibrate channel-wise feature responses based on the category-specific statistics. Finally, a simple yet effective post-processing method is introduced to refine the segmentation results of the proposed attention network. Extensive experiments are performed to justify the effectiveness of the proposed techniques. Most impressively, we achieve state-of-the-art performance on the BraTS 2015 and BraTS 2017 datasets. With the proposed approaches, we also won the joint third place in the BraTS 2018 challenge among 64 participating teams. We will make the code publicly available at https://github.com/chenhong-zhou/OM-Net.

The ability to learn and adapt in real time is a central feature of biological systems. Neuromorphic architectures demonstrating such versatility can greatly enhance our ability to efficiently process information at the edge. A key challenge, however, is to understand which learning rules are best suited for specific tasks and how the relevant hyperparameters can be fine-tuned. In this work, we introduce a conceptual framework in which the learning process is integrated into the network itself. This allows us to cast meta-learning as a mathematical optimization problem. We employ DeepHyper, a scalable, asynchronous model-based search, to simultaneously optimize the choice of meta-learning rules and their hyperparameters. We demonstrate our approach with two different datasets, MNIST and FashionMNIST, using a network architecture inspired by the learning center of the insect brain. Our results show that optimal learning rules can be dataset-dependent even within similar tasks. This dependency demonstrates the importance of introducing versatility and flexibility in the learning algorithms. It also illuminates experimental findings in insect neuroscience that have shown a heterogeneity of learning rules within the insect mushroom body.

In this paper we do the first large scale analysis of writing style development among Danish high school students. More than 10K students with more than 100K essays are analyzed. Writing style itself is often studied in the natural language processing community, but usually with the goal of verifying authorship, assessing quality or popularity, or other kinds of predictions. In this work, we analyze writing style changes over time, with the goal of detecting global development trends among students, and identifying at-risk students. We train a Siamese neural network to compute the similarity between two texts. Using this similarity measure, a student's newer essays are compared to their first essays, and a writing style development profile is constructed for the student. We cluster these student profiles and analyze the resulting clusters in order to detect general development patterns. We evaluate clusters with respect to writing style quality indicators, and identify optimal clusters, showing significant improvement in writing style, while also observing suboptimal clusters, exhibiting periods of limited development and even setbacks. Furthermore, we identify general development trends between high school students, showing that as students progress through high school, their writing style deviates, leaving students less similar when they finish high school, than when they start.

Students hiring ghostwriters to write their assignments is an increasing problem in educational institutions all over the world, with companies selling these services as a product. In this work, we develop automatic techniques with special focus on detecting such ghostwriting in high school assignments. This is done by training deep neural networks on an unprecedented large amount of data supplied by the Danish company MaCom, which covers 90% of Danish high schools. We achieve an accuracy of 0.875 and a AUC score of 0.947 on an evenly split data set.

Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. As the learning signal is weak and our surrogate labels are noisy, we introduce a noise detection component in our model: it lets the model detect and disregard examples which are likely to be noisy. Our method, jointly learning to detect noise and link entities, greatly outperforms the surface matching baseline. For a subset of entity categories, it even approaches the performance of supervised learning.

AI-based solutions offer huge benefits for HR leaders as they seek to deliver high-value services with a limited budget, but HR leaders need to understand (now rather than later) where AI matters most so they can prepare for and take advantage of this rapidly evolving range of technologies. "HR leaders need to reimagine their HR processes and identify ways to mitigate inefficiencies and unlock opportunities for more business-value," says Seyda Berger-Böcker, Director Analyst, Gartner. "When deciding on HR process improvement initiatives, HR leaders must make AI-based solutions a central pillar to look at." HR leaders who embrace AI-based solutions can drive their function's journey toward more operational efficiency The most promising use cases for adopting AI-based solutions are in recruiting, skills management, and learning and development (L&D). Processes in these areas involve a high volume of time-consuming tasks that are still operated by human labor, rely on unstructured data that requires significant HR capacity to analyze, and involve complex decisions that are driven primarily by human judgment or intuition and have some degree of bias.

Real-world applications often combine learning and optimization problems on graphs. For instance, our objective may be to cluster the graph in order to detect meaningful communities (or solve other common graph optimization problems such as facility location, maxcut, and so on). However, graphs or related attributes are often only partially observed, introducing learning problems such as link prediction which must be solved prior to optimization. We propose an approach to integrate a differentiable proxy for common graph optimization problems into training of machine learning models for tasks such as link prediction. This allows the model to focus specifically on the downstream task that its predictions will be used for.

MACKINAC ISLAND – Wednesday at the Mackinac Policy Conference, Gov. Whitmer announced a new program to advance smart infrastructure initiatives and MACKINAC ISLAND – Wednesday at the Mackinac Policy Conference, Gov. Whitmer announced a new program MACKINAC ISLAND – Wednesday at the Mackinac Policy Conference, Gov. Whitmer announced a new program YPSILANTI--The American Society of Mechanical Engineers will sponsor "Electric/Self-Drive Vehicle Technology In Action" Tuesday, May DETROIT - The Michigan Mobility Institute on May 21 announced Wayne State University's College of ANN ARBOR--Four new research grants from the University of Michigan's Graham Sustainability Institute will address LIVONIA--PSI Repair Services Inc., the Livonia-based service provider to the wind energy industry, announced that DETROIT - The Michigan Mobility Institute on May 21 announced Wayne State University's College of LANSING - Michigan Gov. Gretchen Whitmer has agreed to be the keynote speaker June 20 LANSING - Michigan Gov. Gretchen Whitmer has agreed to be the keynote speaker June 20 LANSING - Michigan Gov. Gretchen Whitmer has agreed to be the keynote speaker June 20 LANSING - Michigan Gov. Gretchen Whitmer has agreed to be the keynote speaker June 20 EAST LANSING -- Michigan State University engineering students sounded the channel and won the "foxhunt" LANSING - Michigan's 15 universities would see a 1.9 percent increase under the House version DETROIT - With fuel prices the lowest they've been since the start of the Great

In 1888, the London-based accounting firm that became PricewaterhouseCoopers (PwC) faced a major technological upheaval thanks to the Burroughs adding machine. The first-ever mechanized calculator, an invention by William Seward Burroughs, cut the time to perform accounting tasks in half, and PwC's hundreds of workers had to quickly master the new system, or get left in the dust. Today, PwC isn't simply an accounting firm--now it's a global consultancy with 250,930 employees in 158 countries, raking in $43.1 billion in revenue in 2018--but once again it, along with thousands of other companies, faces a seismic technological shakeup with the advent of AI and other advanced technologies. It's rising to meet the challenge by preparing its workers to use digital technologies at all levels, from entry-level staff to C-suite executives. And it's not alone in its reskilling push--AT&T, IBM, Walmart and other forward-leaning companies also have major retraining programs underway.

Lionbridge, the world's most trusted globalization partner, is pleased to announce the launch of Lionbridge AI. Marrying the market-leading human-annotated AI training data services and linguistic capabilities of Lionbridge, formerly known as Machine Intelligence, with the data training platform and marketplace of recently-acquired Gengo, Lionbridge AI provides a suite of capabilities and services that meets the end-to-end needs of companies building the next generation of machine learning and artificial intelligence (AI) systems. "This is an incredible opportunity to bring together our services, technology platform and voice capabilities into a single offering," said Lionbridge CEO John Fennelly. "We are confident that Lionbridge AI will help our customers deliver improved, more engaging, and increasingly human-like experiences to their artificial intelligence initiatives." As nearly every company contemplates how to use AI to build smarter products and services, while determining how to derive greater predictive capabilities to strengthen the customer experience, Lionbridge AI is perfectly positioned to support the ever-expanding array of uses for artificial intelligence.