Patients with severe Coronavirus disease 19 (COVID-19) typically require supplemental oxygen as an essential treatment. We developed a machine learning algorithm, based on a deep Reinforcement Learning (RL), for continuous management of oxygen flow rate for critical ill patients under intensive care, which can identify the optimal personalized oxygen flow rate with strong potentials to reduce mortality rate relative to the current clinical practice. Basically, we modeled the oxygen flow trajectory of COVID-19 patients and their health outcomes as a Markov decision process. Based on individual patient characteristics and health status, a reinforcement learning based oxygen control policy is learned and real-time recommends the oxygen flow rate to reduce the mortality rate. We assessed the performance of proposed methods through cross validation by using a retrospective cohort of 1,372 critically ill patients with COVID-19 from New York University Langone Health ambulatory care with electronic health records from April 2020 to January 2021. The mean mortality rate under the RL algorithm is lower than standard of care by 2.57% (95% CI: 2.08- 3.06) reduction (P<0.001) from 7.94% under the standard of care to 5.37 % under our algorithm and the averaged recommended oxygen flow rate is 1.28 L/min (95% CI: 1.14-1.42) lower than the rate actually delivered to patients. Thus, the RL algorithm could potentially lead to better intensive care treatment that can reduce mortality rate, while saving the oxygen scarce resources. It can reduce the oxygen shortage issue and improve public health during the COVID-19 pandemic.

As an important part of Artificial Intelligence (AI), Question Answering (QA) aims at generating answers to questions phrased in natural language. While there has been substantial progress in open-domain question answering, QA systems are still struggling to answer questions which involve geographic entities or concepts and that require spatial operations. In this paper, we discuss the problem of geographic question answering (GeoQA). We first investigate the reasons why geographic questions are difficult to answer by analyzing challenges of geographic questions. We discuss the uniqueness of geographic questions compared to general QA. Then we review existing work on GeoQA and classify them by the types of questions they can address. Based on this survey, we provide a generic classification framework for geographic questions. Finally, we conclude our work by pointing out unique future research directions for GeoQA.

The wisdom of the crowd has long become the de facto approach for eliciting information from individuals or experts in order to predict the ground truth. However, classical democratic approaches for aggregating individual \emph{votes} only work when the opinion of the majority of the crowd is relatively accurate. A clever recent approach, \emph{surprisingly popular voting}, elicits additional information from the individuals, namely their \emph{prediction} of other individuals' votes, and provably recovers the ground truth even when experts are in minority. This approach works well when the goal is to pick the correct option from a small list, but when the goal is to recover a true ranking of the alternatives, a direct application of the approach requires eliciting too much information. We explore practical techniques for extending the surprisingly popular algorithm to ranked voting by partial votes and predictions and designing robust aggregation rules. We experimentally demonstrate that even a little prediction information helps surprisingly popular voting outperform classical approaches.

Imagine an automated software that can keep a check on the vaccination data for COVID19. Many of you might be already tapping that nostalgic feel of star wars robotic characters, but "Olive" is developed around reducing repetitive tasks at hospitals. It is a concept that fuses deep learning and computer vision to automate repetitive tasks like documentation, seeking approval before surgeries, and more. Such concepts can be leveraged to document vaccinations across the world. But, robotic applications are not limited to automation in repetitive tasks, and the kiosks from Sanofi are one example. The pharmaceutical giant has created an autonomous inoculation booth like a photo booth.

As the influence and use of artificial intelligence (AI) have grown As the influence and use of artificial intelligence (AI) have grown and its transformative potential has become more apparent, many and its transformative potential has become more apparent [32, 54], questions have been raised regarding the economic, political, social, many questions have been raised regarding the economic, political, and ethical implications of its use. Public opinion plays an important social, and ethical implications of its use [27]. The development role in these discussions, influencing product adoption, commercial and application of AI increasingly features in media, academic, development, research funding, and regulation. In this paper we industrial, regulatory, and public discussions [18, 23, 28], with active present results of an in-depth survey of public opinion of artificial debate on wide-ranging issues such as the impact of automation intelligence conducted with 10,005 respondents spanning eight on the future of work [8, 50, 52], the interaction of AI with human countries and six continents. We report widespread perception rights issues such as privacy and discrimination [1, 4, 10, 16], the that AI will have significant impact on society, accompanied by ethics of autonomous weapons [53, 59], and the development and strong support for the responsible development and use of AI, and availability of dual-use technologies such as synthetic media that also characterize the public's sentiment towards AI with four key may be used for either benevolent or nefarious purposes [48].

Human motion prediction aims to forecast future human poses given a prior pose sequence. The discontinuity of the predicted motion and the performance deterioration in long-term horizons are still the main challenges encountered in current literature. In this work, we tackle these issues by using a compact manifold-valued representation of human motion. Specifically, we model the temporal evolution of the 3D human poses as trajectory, what allows us to map human motions to single points on a sphere manifold. To learn these non-Euclidean representations, we build a manifold-aware Wasserstein generative adversarial model that captures the temporal and spatial dependencies of human motion through different losses. Extensive experiments show that our approach outperforms the state-of-the-art on CMU MoCap and Human 3.6M datasets. Our qualitative results show the smoothness of the predicted motions.

Artificial Intelligence techniques powered by deep neural nets have achieved much success in several application domains, most significantly and notably in the Computer Vision applications and Natural Language Processing tasks. Surpassing human-level performance propelled the research in the applications where different modalities amongst language, vision, sensory, text play an important role in accurate predictions and identification. Several multimodal fusion methods employing deep learning models are proposed in the literature. Despite their outstanding performance, the complex, opaque and black-box nature of the deep neural nets limits their social acceptance and usability. This has given rise to the quest for model interpretability and explainability, more so in the complex tasks involving multimodal AI methods. This paper extensively reviews the present literature to present a comprehensive survey and commentary on the explainability in multimodal deep neural nets, especially for the vision and language tasks. Several topics on multimodal AI and its applications for generic domains have been covered in this paper, including the significance, datasets, fundamental building blocks of the methods and techniques, challenges, applications, and future trends in this domain

In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner. Recently, there have been some attempts towards a similar goal, e.g., studies on Conversational Agents (CAs) and Conversational Search (CS). However, they either do not address complex information needs, or they are limited to the development of conceptual frameworks and/or laboratory-based user studies. We pursue two goals in this paper: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines, and (2) the development of astate-of-the-art pipeline for conversations with search engines, the Conversations with Search Engines (CaSE), using this dataset. SaaC is built based on a multi-turn conversational search dataset, where we further employ workers from a crowdsourcing platform to summarize each relevant passage into a short, conversational response. CaSE enhances the state-of-the-art by introducing a supporting token identification module and aprior-aware pointer generator, which enables us to generate more accurate responses. We carry out experiments to show that CaSE is able to outperform strong baselines. We also conduct extensive analyses on the SaaC dataset to show where there is room for further improvement beyond CaSE. Finally, we release the SaaC dataset and the code for CaSE and all models used for comparison to facilitate future research on this topic.

Welcome back to the "Life in 2050" series! So far, we've looked at how ongoing developments in science, technology, and geopolitics will be reflected in terms of warfare and the economy. Today, we are shifting gears a little and looking at how the turbulence of this century will affect the way people live from day to day. As noted in the previous two installments, changes in the 21st century will be driven by two major factors. These include the disruption caused by rapidly accelerating technological progress, and the disruption caused by rising global temperatures, and the environmental impact this will have (aka. These factors will be pulling the world in opposite directions, and simultaneously at that.

The graph represents a network of 3,600 Twitter users whose tweets in the requested range contained "InsurTech", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Friday, 14 May 2021 at 12:08 UTC. The requested start date was Friday, 14 May 2021 at 00:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 5-day, 18-hour, 4-minute period from Saturday, 08 May 2021 at 05:55 UTC to Friday, 14 May 2021 at 00:00 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.