In multiagent environments, several decision-making individuals interact while adhering to the dynamics constraints imposed by the environment. These interactions, combined with the potential stochasticity of the agents' decision-making processes, make such systems complex and interesting to study from a dynamical perspective. Significant research has been conducted on learning models for forward-direction estimation of agent behaviors, for example, pedestrian predictions used for collision-avoidance in self-driving cars. However, in many settings, only sporadic observations of agents may be available in a given trajectory sequence. For instance, in football, subsets of players may come in and out of view of broadcast video footage, while unobserved players continue to interact off-screen. In this paper, we study the problem of multiagent time-series imputation, where available past and future observations of subsets of agents are used to estimate missing observations for other agents. Our approach, called the Graph Imputer, uses forward- and backward-information in combination with graph networks and variational autoencoders to enable learning of a distribution of imputed trajectories. We evaluate our approach on a dataset of football matches, using a projective camera module to train and evaluate our model for the off-screen player state estimation setting. We illustrate that our method outperforms several state-of-the-art approaches, including those hand-crafted for football.

Scalable systems for automated driving have to reliably cope with an open-world setting. This means, the perception systems are exposed to drastic domain shifts, like changes in weather conditions, time-dependent aspects, or geographic regions. Covering all domains with annotated data is impossible because of the endless variations of domains and the time-consuming and expensive annotation process. Furthermore, fast development cycles of the system additionally introduce hardware changes, such as sensor types and vehicle setups, and the required knowledge transfer from simulation. To enable scalable automated driving, it is therefore crucial to address these domain shifts in a robust and efficient manner. Over the last years, a vast amount of different domain adaptation techniques evolved. There already exists a number of survey papers for domain adaptation on camera images, however, a survey for LiDAR perception is absent. Nevertheless, LiDAR is a vital sensor for automated driving that provides detailed 3D scans of the vehicle's surroundings. To stimulate future research, this paper presents a comprehensive review of recent progress in domain adaptation methods and formulates interesting research questions specifically targeted towards LiDAR perception.

Enzolytics, Inc. (ENZC) is making a powerful move up the charts in recent days since a brief dip below the $0.10 mark. ENZC is a major league runner and powerhouse stock; over the past few months ENZC has seen a legendary run to recent highs of 0.958 per share as it completes the historic merger between BioClonetics and Enzolytics; the new biotech is getting noticed as its technology for producing fully human monoclonal antibodies is currently being employed to produce anti-SARS-CoV-2 (CoronaVirus) monoclonal antibodies for treating COVID-19. With each day of progression of the Coronavirus pandemic, the dire need for multiple active therapeutics becomes more evident. ENZC is a pioneer in using monoclonal antibodies for treating COVID-19. ENZC has partnered with Intel to publish a white paper titled, "Optimizing Empathetic A.I. to Cure Deadly Diseases," highlighting Intel's Artificial Intelligence Analytic tools and Enzolytic's innovative approach and groundbreaking contributions to create universal, durable, and broadly effective treatment targeting all virus variants.

In this chapter, we investigate whether unique, optimal decision boundaries can be found. In order to do so, we first have to revisit several fundamental mathematical principles. Regularization is a mathematical tool, which allows us to find unique solutions even for highly ill-posed problems. In order to use this trick, we review norms and how they can be used to steer regression problems. Rosenblatt's Perceptron and Multi-Layer Perceptrons which are also called Artificial Neural Networks inherently suffer from this ill-posedness.

One Concern is a Menlo Park-based benevolent artificial intelligence company with a mission to increase the global community's resilience to natural hazards. Founded at Stanford University, One Concern enables cities, corporations, and citizens to embrace a disaster-free future through AI-enabled technology, policy, and finance. By combining data science and natural phenomena science we are pursuing a vision for planetary-scale resilience, where everyone lives in a safe, equitable, and sustainable world. One Concern is growing rapidly and we are looking for a passionate and motivated Staff Data Scientist for Risk Simulation to join our team. What you will do Build a global-scale resilience model to predict the societal and economic impact and recovery of the built environment against disasters Work with and support domain experts and data scientists in different hazard products Work with a group of data scientists to develop a risk simulation platform Demonstrate up-to-date modeling techniques and apply this to the development, execution, and improvement of action plans Assess the potential usefulness and validity of new statistical approaches and data sources.

Welcome to the June edition of the ‚Machine-Learning-Collage' series, where I provide an overview of the different Deep Learning research streams. So what is a ML collage? Simply put, I draft one-slide visual summaries of one of my favourite recent papers. At the end of the month all of the resulting visual collages are collected in a summary blog post. Thereby, I hope to give you a visual and intuitive deep dive into some of the coolest trends. May has been quite the month including the virtual ICLR 2021 conference, ICML review decisions as well as the NeurIPS deadlines.

Question answering (QA) systems provide a way of querying the information available in various formats including, but not limited to, unstructured and structured data in natural languages. It constitutes a considerable part of conversational artificial intelligence (AI) which has led to the introduction of a special research topic on Conversational Question Answering (CQA), wherein a system is required to understand the given context and then engages in multi-turn QA to satisfy the user's information needs. Whilst the focus of most of the existing research work is subjected to single-turn QA, the field of multi-turn QA has recently grasped attention and prominence owing to the availability of large-scale, multi-turn QA datasets and the development of pre-trained language models. With a good amount of models and research papers adding to the literature every year recently, there is a dire need of arranging and presenting the related work in a unified manner to streamline future research. This survey, therefore, is an effort to present a comprehensive review of the state-of-the-art research trends of CQA primarily based on reviewed papers from 2016-2021.

This event is part of the Demystifying regulation and commercialisation mini-series, hosted through the Christabel Pankhurst Institute for Health Technology Research and Innovation. These events, taking place in June and July 2021, are organised by Advanced Materials in Medicine (AMM), Translation Manchester, Digital Futures, the University of Manchester Innovation Factory, and the Institute of Data Science and AI. Significant AI health technology activity is taking place in the Greater Manchester (GM) region across academic institutions, regional government, SMEs and larger organisations. Examples include the development of the Greater Manchester Care Records (GMCR), which integrates primary, secondary and social care data from 2.8M individuals and the recent establishment of the Christabel Pankhurst Institute for Health Technology Research and Innovation (Pankhurst), a cross-sector multi-partner translational enabler; and the European Regional Development Funded Greater Manchester Research and Innovation Health Accelerator to support regional SMEs. Due to these developments, there is increasing awareness of the emerging evidence requirements to demonstrate the utility of AI-based health technology but less detailed understanding of the specifics of this complex and evolving environment.

Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize the stated objective in ways that may result in undesirable outcomes. We contend that to learn to act safely, a reinforcement learning (RL) agent should include contemplation of the impact of its actions on the wellbeing and agency of others in the environment, including other acting agents and reactive processes. We endow RL agents with the ability to contemplate such impact by augmenting their reward based on expectation of future return by others in the environment, providing different criteria for characterizing impact. We further endow these agents with the ability to differentially factor this impact into their decision making, manifesting behavior that ranges from self-centred to self-less, as demonstrated by experiments in gridworld environments.

Gromov-Wasserstein (GW) distance is a key tool for manifold learning and cross-domain learning, allowing the comparison of distributions that do not live in the same metric space. Because of its high computational complexity, several approximate GW distances have been proposed based on entropy regularization or on slicing, and one-dimensional GW computation. In this paper, we propose a novel approach for comparing two incomparable distributions, that hinges on the idea of distributional slicing, embeddings, and on computing the closed-form Wasserstein distance between the sliced distributions. We provide a theoretical analysis of this new divergence, called distributional sliced embedding (DSE) discrepancy, and we show that it preserves several interesting properties of GW distance including rotation-invariance. We show that the embeddings involved in DSE can be efficiently learned. Finally, we provide a large set of experiments illustrating the behavior of DSE as a divergence in the context of generative modeling and in query framework.