Peng Zhao Abstract In order to cope with the task allocation in national economic mobilization, a task allocation planning method based on Hierarchical Task Network (HTN) for national economic mobilization is proposed. An HTN planning algorithm is designed to solve and optimize task allocation, and a method is explored to deal with the resource shortage. Finally, based on a real task allocation case in national economic mobilization, an experimental study verifies the effectiveness of the proposed method.

Deterministic planning assumes that the planning evolves along a fully predictable path, and therefore it loses the practical value in most real projections. A more realistic view is that planning ought to take into consideration partial observability beforehand and aim for a more flexible and robust solution. What is more significant, it is inevitable that the quality of plan varies dramatically in the partially observable environment. In this paper we propose a probabilistic contingent Hierarchical Task Network (HTN) planner, named High-Quality Contingent Planner (HQCP), to generate high-quality plans in the partially observable environment. The formalisms in HTN planning are extended into partial observability and are evaluated regarding the cost. Next, we explore a novel heuristic for high-quality plans and develop the integrated planning algorithm. Finally, an empirical study verifies the effectiveness and efficiency of the planner both in probabilistic contingent planning and for obtaining high-quality plans.

Labeling a large number of electronic health records is expensive and time consuming, and having a labeling assistant tool can significantly reduce medical experts' workload. Nevertheless, to gain the experts' trust, the tool must be able to explain the reasons behind its outputs. Motivated by this, we introduce Explainable Labeling Assistant (XLabel) a new visual-interactive tool for data labeling. At a high level, XLabel uses Explainable Boosting Machine (EBM) to classify the labels of each data point and visualizes heatmaps of EBM's explanations. As a case study, we use XLabel to help medical experts label electronic health records with four common non-communicable diseases (NCDs). Our experiments show that 1) XLabel helps reduce the number of labeling actions, 2) EBM as an explainable classifier is as accurate as other well-known machine learning models outperforms a rule-based model used by NCD experts, and 3) even when more than 40% of the records were intentionally mislabeled, EBM could recall the correct labels of more than 90% of these records.

NHSX has laid out its vision, approach and areas of focus for developing a new National Strategy for AI in Health and Social Care. The NHS AI Lab is currently working on a plan that will outline its ambitions for the'development, implementation, scaling and monitoring of AI-driven technologies' in the UK. The organisation has created a draft strategy to support the ultimate goal of deploying AI at scale, in an'effective' and'ethical' way. According to NHSX, its research will consist of three phases: research to understand the current digital health landscape; discussions with those who will use or feel the impact of the new technologies; and looking into possible'futures' for AI. A team of stakeholders, a selection of people involved in the development and deployment of AI in health, as well as potential users of the technologies, have formed a working group to help guide the development of the strategy.

Neil Daly, CEO and Founder of Skin Analytics, added: "We know that skin cancer disproportionately affects younger people and outdoor workers are at a higher risk again. We're delighted to be part of this initiative and use our cutting-edge AI to simplify the process for construction workers to get access to rapid skin cancer assessments." The region has also recently started its launch of eRedbook, to support parents digitally track their baby's growth, vaccinations, and development. Initially launched in Southend, the project will now be gradually rolled out across Essex. Hannah Barber, maternity lead at Mid and South Essex University Hospitals Group, said: "The eRedbook is a huge step-change for new parents to enable them to access important records about their baby's health and development from a mobile app. Giving parents a resource to manage interactive data and access real-time information and guidance as their child grows is particularly exciting and we are thrilled to see Southend as the first area in Essex to launch the technology."

The Department of Health and Social Care has announced a £36 million increase in funding for AI technology-based healthcare services and products. Sir Simon Stevens, Chief Executive of NHS England, said: "Through our NHS AI Lab we're now backing a new generation of groundbreaking but practical solutions to some of the biggest challenges in healthcare. Precision cancer diagnosis, accurate surgery, and new ways of offering mental health support are just a few of the promising real-world patient benefits. Because as the NHS comes through the pandemic, rather than a return to old ways, we're supercharging a more innovative future." "So today our message to developers worldwide is clear – the NHS is ready to help you test your innovations and ensure our patients are among the first in the world to benefit from new AI technologies."

Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.

The Royal College of GPs is inviting clinicians and healthcare professionals in primary care to provide insight on how AI will impact them. Together with UCL, the RCGP is in the early stages of piloting an AI tool for educational purposes. However the College has called for help, via a survey and working group, in testing this tool and providing insight into how work in primary care might be impacted by the introduction of AI more widely. The College is forming an online community to test and support artificial intelligence (AI) activities, including the chatbot AI tool for education. Across the UK significant effort is being expended to develop AI for example the Department of Health Northern Ireland is investing in Queens University Belfast to support AI for precision medicine.

While Hierarchical Task Networks are frequently cited as flexible and powerful planning models, they are often ignored due to the intensive labor cost for experts/programmers, due to the need to create and refine the model by hand. While recent work has begun to address this issue by working towards learning aspects of an HTN model from demonstration, or even the whole framework, the focus so far has been on simple domains, which lack many of the challenges faced in the real world such as imperfect information and real-time environments. I plan to extend this work using the domain of real-time strategy (RTS) games, which have gained recent popularity as a challenging and complex domain for AI research.

We present a system that integrates robot task execution with user input and feedback at multiple abstraction levels in order to achieve greater adaptability in new environments. The user can specify a hierarchical task, with the system interactively proposing logical action groupings within the task. During execution, if tasks fail because objects specified in the initial task description are not found in the environment, the robot proposes substitutions autonomously in order to repair the plan and resume execution. The user can assist the robot by reviewing substitutions. Finally, the user can train the robot to recognize and manipulate novel objects, either during training or during execution. In addition to this single-user scenario, we propose extensions that leverage crowdsourced input to reduce the need for direct user feedback.