Multi-label sentences (text) in the clinical domain result from the rich description of scenarios during patient care. The state-of-theart methods for assertion detection mostly address this task in the setting of a single assertion label per sentence (text). In addition, few rules based and deep learning methods perform negation/assertion scope detection on single-label text. It is a significant challenge extending these methods to address multi-label sentences without diminishing performance. Therefore, we developed a convolutional neural network (CNN) architecture to localize multiple labels and their scopes in a single stage end-to-end fashion, and demonstrate that our model performs atleast 12% better than the state-of-the-art on multi-label clinical text.

Their importance has been highlighted in recent times, when ICUs around the world have been overrun by the COVID-19 pandemic [1, 2]. It is in times like these when research into ways to adequately manage scarce critical care resources must be even more vigorously pursued, in order to offer additional tools that support medical decisions and allow for the effective benchmark of clinical practice. The issue of mortality prediction in the ICU has been approached from a statistical standpoint by means of risk prediction models like APACHE, SAPS, MODS, among others [3]. These models use a set of physiological predictors, demographic factors, and the occurrence of certain chronic conditions, to estimate a score that serves as a proxy for the likelihood of death of ICU patients. Because of the relatively straightforward way of interpreting results, simple statistical approaches such as logistic regression are the go-to modeling techniques used to estimate mortality probability and the importance of the predictors involved. On the other hand, the simplicity of the models also mean that their limited expressiveness may not accurately represent the possibly nonlinear dynamics of mortality prediction. Given this, high-capacity machine learning models might be useful to increase predictive performance.

The RNN transducer is a promising end-to-end model candidate. We compare the original training criterion with the full marginalization over all alignments, to the commonly used maximum approximation, which simplifies, improves and speeds up our training. We also generalize from the original neural network model and study more powerful models, made possible due to the maximum approximation. We further generalize the output label topology to cover RNN-T, RNA and CTC. We perform several studies among all these aspects, including a study on the effect of external alignments. We find that the transducer model generalizes much better on longer sequences than the attention model. Our final transducer model outperforms our attention model on Switchboard 300h by over 6% relative WER.

Spatio-temporal sequence forecasting is one of the fundamental tasks in spatio-temporal data mining. It facilitates many real world applications such as precipitation nowcasting, citywide crowd flow prediction and air pollution forecasting. Recently, a few Seq2Seq based approaches have been proposed, but one of the drawbacks of Seq2Seq models is that, small errors can accumulate quickly along the generated sequence at the inference stage due to the different distributions of training and inference phase. That is because Seq2Seq models minimise single step errors only during training, however the entire sequence has to be generated during the inference phase which generates a discrepancy between training and inference. In this work, we propose a novel curriculum learning based strategy named Temporal Progressive Growing Sampling to effectively bridge the gap between training and inference for spatio-temporal sequence forecasting, by transforming the training process from a fully-supervised manner which utilises all available previous ground-truth values to a less-supervised manner which replaces some of the ground-truth context with generated predictions. To do that we sample the target sequence from midway outputs from intermediate models trained with bigger timescales through a carefully designed decaying strategy. Experimental results demonstrate that our proposed method better models long term dependencies and outperforms baseline approaches on two competitive datasets.

In scenarios that require teamwork, we usually have at hand a variety of specific tasks, for which we need to form a team in order to carry out each one. Here we target the problem of matching teams with tasks within the context of education, and specifically in the context of forming teams of students and allocating them to internship programs. First we provide a formalization of the Team Allocation for Internship Programs Problem, and show the computational hardness of solving it optimally. Thereafter, we propose TAIP, a heuristic algorithm that generates an initial team allocation which later on attempts to improve in an iterative process. Moreover, we conduct a systematic evaluation to show that TAIP reaches optimality, and outperforms CPLEX in terms of time.

Path and motion planning for autonomous systems has long been an area of research within the robotics and artificial intelligence communities. This has led to the development of a number of frameworks which formulate planning tasks in terms of mathematical optimization problems, which can then be solved by utilizing approaches from optimization theory and optimal control [1, 2]. However, planning in complex domains can be a challenging problem, and requires the agents to spend time and computational resources in order to find solutions, leading to an intrinsic need to balance computational complexity and optimality [3, 4, 5, 6, 7]. Within the path-planning community, this observation has resulted in the development of a number of approaches, which aim to explicitly capture the interplay between complexity and optimality. For example, in [8, 5, 9], the authors utilize wavelets to obtain multi-resolution representations of a two-dimensional environment for path-planning.

Markov decision processes are of major interest in the planning community as well as in the model checking community. But in spite of the similarity in the considered formal models, the development of new techniques and methods happened largely independently in both communities. This work is intended as a beginning to unite the two research branches. We consider goal-reachability analysis as a common basis between both communities. The core of this paper is the translation from Jani, an overarching input language for quantitative model checkers, into the probabilistic planning domain definition language (PPDDL), and vice versa from PPDDL into Jani. These translations allow the creation of an overarching benchmark collection, including existing case studies from the model checking community, as well as benchmarks from the international probabilistic planning competitions (IPPC). We use this benchmark set as a basis for an extensive empirical comparison of various approaches from the model checking community, variants of value iteration, and MDP heuristic search algorithms developed by the AI planning community. On a per benchmark domain basis, techniques from one community can achieve state-ofthe-art performance in benchmarks of the other community. Across all benchmark domains of one community, the performance comparison is however in favor of the solvers and algorithms of that particular community. Reasons are the design of the benchmarks, as well as tool-related limitations. Our translation methods and benchmark collection foster crossfertilization between both communities, pointing out specific opportunities for widening the scope of solvers to different kinds of models, as well as for exchanging and adopting algorithms across communities.

Data, meaningful data is the coveted, vital holy grail of Analytics and Data Driven Marketing. Jepto is the newest artificial intelligence and predictive analytics marketing tool that is the first of its kind, using machine learning to monitor KPI and predict whether they will be met or will fall short. There have been a number of platforms which try to use artificial intelligence, such as Crystal, which I have used. It was a terrible product and did not do anything useful. Jepto, on the other hand has so many benefits and is well thought out, yet friendly to users with an easy onboarding process, this is a piece of software agencies and serious online marketers have to watch out for.

Dr. David Bray is the Inaugural Director of the new global GeoTech Center & Commission of the Atlantic Council, a nonprofit for international political, business, and intellectual leaders founded in 1961. Headquartered in Washington, DC, the Council offers programs related to international security and global economic prosperity. In previous leadership roles, Bray led the technology aspects of the Centers for Disease Control's bioterrorism preparedness program in response to 9/11, the outbreak response to the West Nile virus, SARS, monkey pox and other emergencies. He also spent time on the ground in Afghanistan in 2009 as a senior advisor to both military and humanitarian assistance efforts, serving as the non-partisan Executive Director for a bipartisan National Commission on R&D, and providing leadership as a non-partisan federal agency Senior Executive focused on digital modernization. He also is a Young Global Leader for 2017-2021 of the World Economic Forum. Bray is a member of multiple Boards of Directors and has worked with the U.S. Special Operations Command on counter-misinformation efforts. He was invited to give the 2019 UN Charter Keynote on the future of AI & IoT governance. His academic background includes a PhD from Emory University; he also has held affiliations with MIT, Harvard, and the University of Oxford. He recently took a few moments to speak to AI Trends Editor John P. Desmond about current events, including the geopolitics of the COVID-19 pandemic. AI Trends: Thank you David for talking to AI Trends today.

Over the last several years, the use of artificial intelligence (AI) and machine learning (ML) has maintained consistent growth among businesses. During our 2017 survey of IT decision makers in the United States and Japan, we discovered that approximately 74% of businesses in both regions were already using some form of AI or ML to protect their organizations from cyber threats. When we checked in with both regions at the end of 2018, 73% of respondents we surveyed reported they planned to use even more AI/ML tools in the following year. For this report, we surveyed 800 IT professionals with cybersecurity decision-making power across the US, UK, Japan, and Australia/New Zealand regions at the end of 2019, and discovered that 96% of respondents now use AI/ML tools in their cybersecurity programs. Despite the increase in adoption rates for these technologies, more than half of IT decision makers admitted they do not fully understand the benefits of these tools.