Recent empirical and theoretical studies have shown that many learning algorithms -- from linear regression to neural networks -- can have test performance that is non-monotonic in quantities such the sample size and model size. This striking phenomenon, often referred to as "double descent", has raised questions of if we need to re-think our current understanding of generalization. In this work, we study whether the double-descent phenomenon can be avoided by using optimal regularization. Theoretically, we prove that for certain linear regression models with isotropic data distribution, optimally-tuned $\ell_2$ regularization achieves monotonic test performance as we grow either the sample size or the model size. We also demonstrate empirically that optimally-tuned $\ell_2$ regularization can mitigate double descent for more general models, including neural networks. Our results suggest that it may also be informative to study the test risk scalings of various algorithms in the context of appropriately tuned regularization.

In this paper we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After a general introduction, we motivate and contrast various graph-based data models and query languages that are used for knowledge graphs. We discuss the roles of schema, identity, and context in knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We summarise methods for the creation, enrichment, quality assessment, refinement, and publication of knowledge graphs. We provide an overview of prominent open knowledge graphs and enterprise knowledge graphs, their applications, and how they use the aforementioned techniques. We conclude with high-level future research directions for knowledge graphs.

How have publishers evolved and what do they see ahead? Amid rising fears that artificial intelligence (AI) will threaten journalists' jobs and take over the newsroom, the Journalism AI report – a project by Polis in collaboration with Google News Initiative – sought to find out how exactly AI technologies are being applied to journalism. However, AI is a'significant part of journalism already but it is unevenly distributed' and news organizations are already applying aspects of intelligent technology in their operations, to help them work more efficiently and improve monetization. "One of the key aspects of AI and journalism is that it allows the whole journalism model to become more holistic, with a feedback loop between the different parts of the production and dissemination process" Artificial intelligence systems can be useful in helping newsrooms to categorize content or information at scale for different news gathering purposes. For example, since 2015 The Associated Press have been using a management tool, SAM, which algorithmically sifts through social media platforms to alert the newsroom on likely breaking news events.

Global Artificial Intelligence and Machine Learning Market 2020, presents a professional and in-depth study on the current state of the industry globally, providing basic overview of Artificial Intelligence and Machine Learning market including definitions, classifications, applications and industry chain structure. The report compares this data with the current state of the Artificial Intelligence and Machine Learning market and thus discuss upon the upcoming trends that have brought the Artificial Intelligence and Machine Learning market transformation. Industry predictions along with the statistical implication presented in the report delivers an accurate scenario of the Artificial Intelligence and Machine Learning market. The market forces determining the shaping of the worldwide Artificial Intelligence and Machine Learning market have been evaluated in detail. In addition to this, the supervisory outlook of the Artificial Intelligence and Machine Learning market has been covered in the report from both the Global and local perspective.

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a downstream task. However, human populations learn to solve complex tasks involving communicative behaviors not only in fully cooperative settings but also in scenarios where competition acts as an additional external pressure for improvement. In this work, we investigate whether competition for performance from an external, similar agent team could act as a social influence that encourages multi-agent populations to develop better communication protocols for improved performance, compositionality, and convergence speed. We start from Task & Talk, a previously proposed referential game between two cooperative agents as our testbed and extend it into Task, Talk & Compete, a game involving two competitive teams each consisting of two aforementioned cooperative agents. Using this new setting, we provide an empirical study demonstrating the impact of competitive influence on multi-agent teams. Our results show that an external competitive influence leads to improved accuracy and generalization, as well as faster emergence of communicative languages that are more informative and compositional.

To the untrained eye, zebras in Kenya probably all look alike. But each animal's black and white markings are like a fingerprint, distinct -- and invaluable for scientists who need to track the animals and information about them, including their births, deaths, health and migration patterns. Traditionally, getting this kind of information has been an invasive and labor-intensive process. But breakthroughs in artificial intelligence (AI) and crowdsourcing of photos of individual animals are beginning to change the conservation game. Portland, Oregon-based nonprofit Wild Me has developed AI to pick out identifying markers -- the stripes on a zebra, the spots on a giraffe, the contours of a flukewhale's fin -- and catalog animals much faster than a human can.

Deep Neural Networks (NNs) with many hidden layers are now at the core of modern machine learning applications and can achieve remarkable performance that was previously unattainable using shallow networks. But why are deeper networks better than shallow? Perhaps intuitively, one can understand that the nature of computation done by deep and shallow networks is different; simple one hidden layer NNs extract independent features of the input and return their weighted sum, while deeper NNs can compute features of features, making the features computed by deeper layers no longer independent. Another line of intuition (Poole et al. (2016)), is that highly complicated manifolds in input space can actually turn into flattened manifolds in hidden space, thus helping with downstream tasks (e.g., classification). To make the above intuitions formal and understand the benefits of depth, researchers try to understand the expressivity of NNs and prove depth separation results. Early results in this area sometimes referred to as universality theorems (Cybenko, 1989; Hornik et al., 1989), state that NNs of just one hidden layer, equipped with standard activation units (e.g., sigmoids, ReLUs etc.) are "dense" in the space of continuous functions, meaning that any continuous function can be represented by an appropriate combination of these activation units.

We present ProxEmo, a novel end-to-end emotion prediction algorithm for socially aware robot navigation among pedestrians. Our approach predicts the perceived emotions of a pedestrian from walking gaits, which is then used for emotion-guided navigation taking into account social and proxemic constraints. To classify emotions, we propose a multi-view skeleton graph convolution-based model that works on a commodity camera mounted onto a moving robot. Our emotion recognition is integrated into a mapless navigation scheme and makes no assumptions about the environment of pedestrian motion. It achieves a mean average emotion prediction precision of 82.47% on the Emotion-Gait benchmark dataset. We outperform current state-of-art algorithms for emotion recognition from 3D gaits. We highlight its benefits in terms of navigation in indoor scenes using a Clearpath Jackal robot.

Artificial Moral Agents (AMA's) is a field in computer science with the purpose of creating autonomous machines that can make moral decisions akin to how humans do. Researchers have proposed theoretical means of creating such machines, while philosophers have made arguments as to how these machines ought to behave, or whether they should even exist. Of the currently theorised AMA's, all research and design has been done with either none or at most one specified normative ethical theory as basis. This is problematic because it narrows down the AMA's functional ability and versatility which in turn causes moral outcomes that a limited number of people agree with (thereby undermining an AMA's ability to be moral in a human sense). As solution we design a three-layer model for general normative ethical theories that can be used to serialise the ethical views of people and businesses for an AMA to use during reasoning. Four specific ethical norms (Kantianism, divine command theory, utilitarianism, and egoism) were modelled and evaluated as proof of concept for normative modelling. Furthermore, all models were serialised to XML/XSD as proof of support for computerisation.

Given the large variety of existing logical formalisms it is of utmost importance to select the most adequate one for a specific purpose, e.g. for representing the knowledge relevant for a particular application or for using the formalism as a modeling tool for problem solving. Awareness of the nature of a logical formalism, in other words, of its fundamental intrinsic properties, is indispensable and provides the basis of an informed choice. One such intrinsic property of logic-based knowledge representation languages is the context-dependency of pieces of knowledge. In classical propositional logic, for example, there is no such context-dependence: whenever two sets of formulas are equivalent in the sense of having the same models (ordinary equivalence), then they are mutually replaceable in arbitrary contexts (strong equivalence). However, a large number of commonly used formalisms are not like classical logic which leads to a series of interesting developments.