Permission to make digital or hard copies of part or all of thi s work for personal or classroom use is granted without fee provided that copies ar e not made or distributed for profit or commercial advantage and that copies bear this n otice and the full citation on the first page. CSCW'19,, November 9th-13th 2019, Austin, T exas ACM 978-1-4503-6819-3/20/04. https://doi.org/10.1145/3334480.XXXXXXX Abstract While machine learning (ML) systems have produced great advances in several domains, their use in support of complex cooperative work remains a research challenge. A particularly challenging setting, and one that may benefit from ML support is the work of multidisciplinary medical teams (MDTs). This paper focuses on the activities performed during the multidisciplinary medical team meeting (MDTM), reviewing their main characteristics in light of a longitud inal analysis of several MDTs in a large teaching hospital over a period of ten years and of our development of ML methods to support MDTMs, and identifying opportunities and possible pitfalls for the use of ML to support MDTMs. Author Keywords Machine Learning; Speech and Language Processing; Mul-tidisciplinary Medical T eam Meeting; Collaboration Introduction An MDT is a group of specialists from different healthcare professions who collaborate on diagnosis and treatment of patients in their care.

The challenges of such a problem involve understanding the nuances of interaction between the multiple modalities, and handling a real-time retrieval from large-scale catalog. While neural models with their rich express-ibility to encode such complex modalities, have revolution-alized research on complex multimodal tasks, the standard practices of end-to-end pure neural style training fails to explicitly model the latent structures present in the different modalities or the different strategies required for the complex task. Without so, the neural model can make blatant mistakes, which its earlier symbolic counterparts would not have made. In this work, we propose a neural symbolic approach for modeling a caption based image retrieval task. The backbone of such a modeling requires a scene-graph representation, [3] of the image catalog and the ongoing di-1 Indian Institute of Technology, Madras 2 IBM Research Labs, Bangalore 3 Indian Institute of Technology, Bombay alog context, and the retrieval task is modeled as a graph subsumption problem.

Two hitherto disconnected threads of research, diverse exploration (DE) and maximum entropy RL have addressed a wide range of problems facing reinforcement learning algorithms via ostensibly distinct mechanisms. In this work, we identify a connection between these two approaches. First, a discriminator-based diversity objective is put forward and connected to commonly used divergence measures. We then extend this objective to the maximum entropy framework and propose an algorithm Maximum Entropy Diverse Exploration (MEDE) which provides a principled method to learn diverse behaviors. A theoretical investigation shows that the set of policies learned by MEDE capture the same modalities as the optimal maximum entropy policy. In effect, the proposed algorithm disentangles the maximum entropy policy into its diverse, constituent policies. Experiments show that MEDE is superior to the state of the art in learning high performing and diverse policies.

-- Understanding multi-vehicle interactive behaviors with temporal sequential observations is crucial for autonomous vehicles to make appropriate decisions in an uncertain traffic environment. On-demand similarity measures are significant for autonomous vehicles to deal with massive interactive driving behaviors by clustering and classifying diverse scenarios. This paper proposes a general approach for measuring spatiotemporal similarity of interactive behaviors using a multivariate matrix profile technique. The key attractive features of the approach are its superior space and time complexity, real-time online computing for streaming traffic data, and possible capability of leveraging hardware for parallel computation. The proposed approach is validated through automatically discovering similar interactive driving behaviors at intersections from sequential data. One of the biggest challenges for deploying autonomous vehicles (A Vs) in real life is the requirement of the A Vs' capability to interact with surrounding road users. Classifying diverse scenarios and separately designing appropriate decisions using on-hand prior knowledge is unfortunately not realistic [1] because of the diversity of scenarios that are far larger and messier than human beings can cope with [2].

Who's involved: Specialist insurer Hiscox. What's happening: Hiscox has developed an app – FloodPlus AR – that uses augmented reality technology to illustrate the growing flood threat to coastal towns and cities from rising sea levels. Significance of development: The app allows people to see how predicted sea level rises could affect Greenville, a suburb of Jersey City in the US, using a virtual topographical map. According to Hiscox's analysis, 8.8% of properties in Hudson County, New Jersey, could be flooded if global sea levels rose by the 2.4 metres, as predicted by some climate experts by the end of this century. Who's involved: Israeli startup Ride Vision and Italian insurance provider, Sara Assicurazioni.

The graph represents a network of 3,855 Twitter users whose tweets in the requested range contained "#iot OR "internet of things"", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Saturday, 02 November 2019 at 21:34 UTC. The requested start date was Friday, 01 November 2019 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 5,000. The tweets in the network were tweeted over the 1-day, 3-hour, 59-minute period from Wednesday, 30 October 2019 at 20:01 UTC to Friday, 01 November 2019 at 00:01 UTC.

Mark Kingwell is a professor of philosophy at the University of Toronto. More than five decades ago, Marshall McLuhan argued that media are ecosystems, extensions of human consciousness. The famous adage that the medium is the message also means, as the often-misquoted title of McLuhan's famous book notes, that the medium is the mass age. We are all immersed in media and technology. Media have changed a lot since McLuhan wrote: less broadcast, more diffusion and unruliness.

LinkedIn cofounder and Greylock Partners investor Reid Hoffman tells executives who are running startups that scale fast -- the kind who want to double in size every few months -- to build ethics into their businesses. As companies plan for the future and grow their engineering or sales ranks, they should consider what can go wrong, he said, and hire people whose job is dedicated to risk management. Next, he added, companies can develop a risk framework to sort risk levels. Anything that can be a catastrophic risk to individuals, a systemic risk to company systems, or a risk to a large number of users should be handled in a proactive way to stay competitive with other startups. Hoffman, who coauthored the book Blitzscaling, joined former White House chief data scientist DJ Patil and Stanford University political science professor Amy Zegart Tuesday at the Stanford Human-Centered AI Intelligence (HAI) fall conference on AI ethics, governance, and policy symposium at the Hoover Institution in Palo Alto.

This document explores the mathematics of deep convolutional neural networks. We begin at the level of an individual neuron, and from there examine parameter tuning, fully-connected networks, error minimization, back-propagation, convolutional networks, and finally deep networks. The report concludes with experiments on geometric invariance, and data augmentation. Relevant MATLAB code is provided throughout, and a downloadable package is available at the end of the document. Artificial neural networks (ANNs) [1] are at the core of state-of-the-art approaches to a variety of visual recognition tasks, including image classification [2] and object detection [3]. For a computer vision researcher interested in recognition, it is useful to understand how ANNs work, and why they have recently become so effective. An artificial neural network is a type of biologically-inspired pattern recognizer.

The Conference on Empirical Methods in Natural Language Processing (EMNLP) is one of the top natural language processing conferences in the world. In 2019, it is to be held in Hong Kong, China. There were 1,813 long paper submissions, of which 465 were accepted and 1,063 short paper submissions, of which 218 were accepted. A large number of these papers also published their code ( code download link). To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper.