Artificial Intelligence (AI) seems to be a unique technology of making a machine, a robot fully autonomous. AI is an analysis of how the machine is thinking, studying, determining and functioning when it is trying to solve problems. These so-called problems are present in all fields - the most emerging ones in 2020 and even beyond. The aim of Artificial Intelligence (AI) is to enhance machine functions relating to human knowledge, such as reasoning, learning and problems along with the ability to manipulate things. For example, virtual assistants or chatbots offer expert advice.

Some areas in Japan are struggling to secure enough public school staff to teach Japanese to children with foreign roots amid a recent surge in the number of such students in the country, a Kyodo News survey showed Wednesday. The city of Yokohama, Saitama Prefecture and Fukushima Prefecture began the academic years of 2018 and 2019 without enough Japanese-language teachers, with a deficit of 28 in public elementary and junior high schools, according to the survey of local education boards. The three authorities were short by 21, five, and two teachers respectively. Almost all vacancies were able to be filled by the middle of these school years, but the Fukushima education board was unable to fill one spot during the whole of the 2018 academic year. With the number of children without adequate Japanese-language skills on the rise, the education ministry formulated a standard in 2017 that requires schools to have one licensed Japanese-language teacher per 18 students with such needs, aiming to achieve the target gradually over the next 10 years.

AI is changing lives in a multitude of ways, and one of the most important is how we learn. Numerous barriers prevent education from reaching its full potential: money, space, accessibility, etc. This accessibility crisis is no secret. AI offers a promising solution by solving some of these issues: It provides personalized education on an unmatched scale. How is AI shaking up education?

American Sign Language recognition is a difficult gesture recognition problem, characterized by fast, highly articulate gestures. These are comprised of arm movements with different hand shapes, facial expression and head movements. Among these components, hand shape is the vital, often the most discriminative part of a gesture. In this work, we present an approach for effective learning of hand shape embeddings, which are discriminative for ASL gestures. For hand shape recognition our method uses a mix of manually labelled hand shapes and high confidence predictions to train deep convolutional neural network (CNN). The sequential gesture component is captured by recursive neural network (RNN) trained on the embeddings learned in the first stage. We will demonstrate that higher quality hand shape models can significantly improve the accuracy of final video gesture classification in challenging conditions with variety of speakers, different illumination and significant motion blurr. We compare our model to alternative approaches exploiting different modalities and representations of the data and show improved video gesture recognition accuracy on GMU-ASL51 benchmark dataset

Federated learning is a distributed machine learning approach to privacy preservation and two major technical challenges prevent a wider application of federated learning. One is that federated learning raises high demands on communication, since a large number of model parameters must be transmitted between the server and the clients. The other challenge is that training large machine learning models such as deep neural networks in federated learning requires a large amount of computational resources, which may be unrealistic for edge devices such as mobile phones. The problem becomes worse when deep neural architecture search is to be carried out in federated learning. To address the above challenges, we propose an evolutionary approach to real-time federated neural architecture search that not only optimize the model performance but also reduces the local payload. During the search, a double-sampling technique is introduced, in which for each individual, a randomly sampled sub-model of a master model is transmitted to a number of randomly sampled clients for training without reinitialization. This way, we effectively reduce computational and communication costs required for evolutionary optimization and avoid big performance fluctuations of the local models, making the proposed framework well suited for real-time federated neural architecture search.

We evaluate the robustness of a probabilistic formulation of system identification (ID) to sparse, noisy, and indirect data. Specifically, we compare estimators of future system behavior derived from the Bayesian posterior of a learning problem to several commonly used least squares-based optimization objectives used in system ID. Our comparisons indicate that the log posterior has improved geometric properties compared with the objective function surfaces of traditional methods that include differentially constrained least squares and least squares reconstructions of discrete time steppers like dynamic mode decomposition (DMD). These properties allow it to be both more sensitive to new data and less affected by multiple minima --- overall yielding a more robust approach. Our theoretical results indicate that least squares and regularized least squares methods like dynamic mode decomposition and sparse identification of nonlinear dynamics (SINDy) can be derived from the probabilistic formulation by assuming noiseless measurements. We also analyze the computational complexity of a Gaussian filter-based approximate marginal Markov Chain Monte Carlo scheme that we use to obtain the Bayesian posterior for both linear and nonlinear problems. We then empirically demonstrate that obtaining the marginal posterior of the parameter dynamics and making predictions by extracting optimal estimators (e.g., mean, median, mode) yields orders of magnitude improvement over the aforementioned approaches. We attribute this performance to the fact that the Bayesian approach captures parameter, model, and measurement uncertainties, whereas the other methods typically neglect at least one type of uncertainty.

We study "adversarial scaling", a multi-armed bandit model where rewards have a stochastic and an adversarial component. Our model captures display advertising where the "click-through-rate" can be decomposed to a (fixed across time) arm-quality component and a non-stochastic user-relevance component (fixed across arms). Despite the relative stochasticity of our model, we demonstrate two settings where most bandit algorithms suffer. On the positive side, we show that two algorithms, one from the action elimination and one from the mirror descent family are adaptive enough to be robust to adversarial scaling. Our results shed light on the robustness of adaptive parameter selection in stochastic bandits, which may be of independent interest.

Classification is one of the core problems in statistical learning and has been intensively studied in statistical and machine learning literature. Nevertheless, while the theory for binary classification is well developed (see, Devroy, Gyöfri and Lugosi, 1996; Vapnik, 2000; Boucheron, Bousquet and Lugosi, 2005 and references therein for a comprehensive review), its multiclass extensions are much less complete. Consider a general L-class classification with a (high-dimensional) vector of features X X R d and the outcome class label Y {1,..., L}. We can model it as Y (X x) Mult(p 1 (x),..., p L (x)), where p l (x) P (Y l X x), l 1,..., L. A classifier is a measurable function η: X {1,..., L}. The accuracy of a classifier η is defined by a misclassification error R(η) P (Y η(x)). The optimal classifier that minimizes this error is the Bayes classifier η (x) arg max 1 l L p l (x) with R(η) 1 E X max 1 l L p l (x). The probabilities p l (x)'s are, however, unknown and one should derive a classifier η(x) from the available data D: a random sample of n independent observations (X 1, Y 1),..., (X n, Y n) from the joint distribution of (X, Y). The corresponding (conditional) misclassification error of η is R( η) P (Y η(x) D) and the goodness of η w.r.t.

We initiate the study of learning in contextual bandits with the help of loss predictors. The main question we address is whether one can improve over the minimax regret $\mathcal{O}(\sqrt{T})$ for learning over $T$ rounds, when the total error of the predictor $\mathcal{E} \leq T$ is relatively small. We provide a complete answer to this question, including upper and lower bounds for various settings: adversarial versus stochastic environments, known versus unknown $\mathcal{E}$, and single versus multiple predictors. We show several surprising results, such as 1) the optimal regret is $\mathcal{O}(\min\{\sqrt{T}, \sqrt{\mathcal{E}}T^\frac{1}{4}\})$ when $\mathcal{E}$ is known, a sharp contrast to the standard and better bound $\mathcal{O}(\sqrt{\mathcal{E}})$ for non-contextual problems (such as multi-armed bandits); 2) the same bound cannot be achieved if $\mathcal{E}$ is unknown, but as a remedy, $\mathcal{O}(\sqrt{\mathcal{E}}T^\frac{1}{3})$ is achievable; 3) with $M$ predictors, a linear dependence on $M$ is necessary, even if logarithmic dependence is possible for non-contextual problems. We also develop several novel algorithmic techniques to achieve matching upper bounds, including 1) a key action remapping technique for optimal regret with known $\mathcal{E}$, 2) implementing Catoni's robust mean estimator efficiently via an ERM oracle leading to an efficient algorithm in the stochastic setting with optimal regret, 3) constructing an underestimator for $\mathcal{E}$ via estimating the histogram with bins of exponentially increasing size for the stochastic setting with unknown $\mathcal{E}$, and 4) a self-referential scheme for learning with multiple predictors, all of which might be of independent interest.

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.