Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned on task completion. These task-conditioned models adaptively focus modeling capacity on task-relevant dynamics, while simultaneously serving as an effective heuristic for planning with sparse rewards. We evaluate our method on challenging visual goal completion tasks and show a substantial increase in performance compared to prior model-free approaches. Deep reinforcement learning has proven to be a powerful and effective framework for solving a diversity of challenging decision-making problems (Silver et al., 2017a; Berner et al., 2019). However these algorithms are typically trained to maximize a single reward function, ignoring information that is not directly relevant to the associated task at hand. This way of learning is in stark contrast to how humans learn (Tenenbaum, 2018). Without being prompted by a specific task, humans can still explore their environment, practice achieving imaginary goals, and in so doing learn about the dynamics of the environment. When subsequently presented with a novel task, humans can utilize this learned knowledge to bootstrap learning -- a property we would like our artificial agents to have. In this work, we investigate one way to bridge this gap by learning world models (Ha & Schmidhuber, 2018) that enable the realization of previously unseen tasks. By modeling the task-agnostic dynamics of an environment, an agent can make predictions about how its own actions may affect the environment state without the need for additional samples from the environment. Prior work has shown that by using powerful function approximators to model environment dynamics, training an agent entirely within its own world models can result in large gains in sample efficiency (Ha & Schmidhuber, 2018).

HO CHI MINH CITY (Vietnam News/ANN): Vietnam should use artificial intelligence in more areas to boost productivity and to improve people's lives, experts have said. Deputy Minister of Science and Technology Bùi Thế Duy told a conference last Friday (Nov 27) that AI had been receiving more and more attention in recent years, and, along with other modern technologies (such as big data and cloud computing), was changing people's lives and business activities. Covid-19 was creating a push for faster digital transformation, and companies and researchers should consider how using AI solutions could help a recovery after the pandemic, he said. Nguyễn Việt Dũng, director of the HCM City Department of Science and Technology, said the city was among the first in Vietnam to issue a programme to facilitate digital transformation, focusing on promoting AI usage. Dr Stefan Hajkowicz of the Commonwealth Scientific and Industrial Research Organisation said AI could be used in many areas, pointing to how Australia did so in agriculture, mining and aviation.

Event Detection (ED) aims to recognize instances of specified types of event triggers in text. Different from English ED, Chinese ED suffers from the problem of word-trigger mismatch due to the uncertain word boundaries. Existing approaches injecting word information into character-level models have achieved promising progress to alleviate this problem, but they are limited by two issues. First, the interaction between characters and lexicon words is not fully exploited. Second, they ignore the semantic information provided by event labels. We thus propose a novel architecture named Label enhanced Heterogeneous Graph Attention Networks (L-HGAT). Specifically, we transform each sentence into a graph, where character nodes and word nodes are connected with different types of edges, so that the interaction between words and characters is fully reserved. A heterogeneous graph attention networks is then introduced to propagate relational message and enrich information interaction. Furthermore, we convert each label into a trigger-prototype-based embedding, and design a margin loss to guide the model distinguish confusing event labels. Experiments on two benchmark datasets show that our model achieves significant improvement over a range of competitive baseline methods.

The paper introduces the notion of an epistemic argumentation framework (EAF) as a means to integrate the beliefs of a reasoner with argumentation. Intuitively, an EAF encodes the beliefs of an agent who reasons about arguments. Formally, an EAF is a pair of an argumentation framework and an epistemic constraint. The semantics of the EAF is defined by the notion of an ω-epistemic labelling set, where ω is complete, stable, grounded, or preferred, which is a set of ω-labellings that collectively satisfies the epistemic constraint of the EAF. The paper shows how EAF can represent different views of reasoners on the same argumentation framework. It also includes representing preferences in EAF and multi-agent argumentation.

Areas covering algorithms that commonly require measurements of similarity within data include classification, ranking, decision-making and pattern-matching. A similarity measure can effectively substitute for a distance measure (e.g. Euclidean distance), making data types with defined similarity measures compatible with methods such as K-Nearest Neighbour [1, 2] and TOPSIS [3, 4, 5]. This study proposes a similarity measure for aggregate fuzzy numbers constructed from interval-valued data using the Interval Agreement Approach (IAA), that is when given two such fuzzy numbers the degree of similarity regarding them is computed. The experimental interval-valued data in recent literature is often an alternative representation of expert opinion.

Due to researchers'aim to study personalized recommendations for different business fields, the summary of recommendation methods in specific fields is of practical significance. News recommendation systems were the earliest research field regarding recommendation systems, and were also the earliest recommendation field to apply the collaborative filtering method. In addition, news is real-time and rich in content, which makes news recommendation methods more challenging than in other fields. Thus, this paper summarizes the research progress regarding news recommendation methods. From 2018 to 2020, developed news recommendation methods were mainly deep learning-based, attention-based, and knowledge graphs-based. As of 2020, there are many news recommendation methods that combine attention mechanisms and knowledge graphs. However, these methods were all developed based on basic methods (the collaborative filtering method, the content-based recommendation method, and a mixed recommendation method combining the two). In order to allow researchers to have a detailed understanding of the development process of news recommendation methods, the news recommendation methods surveyed in this paper, which cover nearly 10 years, are divided into three categories according to the abovementioned basic methods. Firstly, the paper introduces the basic ideas of each category of methods and then summarizes the recommendation methods that are combined with other methods based on each category of methods and according to the time sequence of research results. Finally, this paper also summarizes the challenges confronting news recommendation systems.

Interpretable machine learning addresses the black-box nature of deep neural networks. Visual prototypes have been suggested for intrinsically interpretable image recognition, instead of generating post-hoc explanations that approximate a trained model. However, a large number of prototypes can be overwhelming. To reduce explanation size and improve interpretability, we propose the Neural Prototype Tree (ProtoTree), a deep learning method that includes prototypes in an interpretable decision tree to faithfully visualize the entire model. In addition to global interpretability, a path in the tree explains a single prediction. Each node in our binary tree contains a trainable prototypical part. The presence or absence of this prototype in an image determines the routing through a node. Decision making is therefore similar to human reasoning: Does the bird have a red throat? And an elongated beak? Then it's a hummingbird! We tune the accuracy-interpretability trade-off using ensembling and pruning. We apply pruning without sacrificing accuracy, resulting in a small tree with only 8 prototypes along a path to classify a bird from 200 species. An ensemble of 5 ProtoTrees achieves competitive accuracy on the CUB-200-2011 and Stanford Cars data sets. Code is available at https://github.com/M-Nauta/ProtoTree

Machine learning-based medical anomaly detection is an important problem that has been extensively studied. Numerous approaches have been proposed across various medical application domains and we observe several similarities across these distinct applications. Despite this comparability, we observe a lack of structured organisation of these diverse research applications such that their advantages and limitations can be studied. The principal aim of this survey is to provide a thorough theoretical analysis of popular deep learning techniques in medical anomaly detection. In particular, we contribute a coherent and systematic review of state-of-the-art techniques, comparing and contrasting their architectural differences as well as training algorithms. Furthermore, we provide a comprehensive overview of deep model interpretation strategies that can be used to interpret model decisions. In addition, we outline the key limitations of existing deep medical anomaly detection techniques and propose key research directions for further investigation.

Standing just 5ft tall, Mitra navigates around the hospital wards, guided by facial recognition technology and with a chest-mounted tablet that allows patients and their loved ones to see each other. Developed in recent years by the Bengaluru startup Invento Robotics, Mitra costs around $13,600 (£10,000) and – due to the reduced risk of infection to doctors – has become hugely popular in Indian hospitals during the pandemic. Since making headlines at its debut in 2017 at an international summit, where it greeted Ivanka Trump and interacted with India's prime minister Narendra Modi, Mitra has increasingly been put to use in hospitals treating Covid-19 patients. "Mitra was originally meant for care homes, but was adapted during the pandemic to assist doctors and nurses by taking vital readings, and to help in consultations," says Balaji Viswanathan, chief executive of Invento Robotics, which now exports the robot to five countries including the US and Australia. India still only has about three robots for every 10,000 workers, but the domestic industry is growing rapidly, fuelled in no small part by the pandemic.

Esports players might be viewed as individuals who sit around, eat junk food and guzzle down sugary drinks, but a new study finds these gamers are just the opposite. A team from Queensland University of Technology uncovered uncovered players are up to 21 percent more likely to have a healthier body weight than the average person. The survey also reveals that esport gamers smoke and drink less than the general public and are significantly more active as a result of certain video games. Although a majority are in tip top shape, the study did find that 4.03 percent of esports players are more likely to be morbidly obese than the general public. A team from Queensland University of Technology uncovered uncovered players are up to 21 percent more likely to have a healthier body weight than the average person.