Cognitive Diagnosis Models (CDMs) are a special family of discrete latent variable models that are widely used in modern educational, psychological, social and biological sciences. A key component of CDMs is a binary $Q$-matrix characterizing the dependence structure between the items and the latent attributes. Additionally, researchers also assume in many applications certain hierarchical structures among the latent attributes to characterize their dependence. In most CDM applications, the attribute-attribute hierarchical structures, the item-attribute $Q$-matrix, the item-level diagnostic model, as well as the number of latent attributes, need to be fully or partially pre-specified, which however may be subjective and misspecified as noted by many recent studies. This paper considers the problem of jointly learning these latent and hierarchical structures in CDMs from observed data with minimal model assumptions. Specifically, a penalized likelihood approach is proposed to select the number of attributes and estimate the latent and hierarchical structures simultaneously. An efficient expectation-maximization (EM) algorithm and a latent structure recovery algorithm are developed, and statistical consistency theory is also established under mild conditions. The good performance of the proposed method is illustrated by simulation studies and a real data application in educational assessment.

The graph represents a network of 2,735 Twitter users whose tweets in the requested range contained "#FinServ", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Sunday, 04 April 2021 at 01:32 UTC. The requested start date was Sunday, 04 April 2021 at 00:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 11-day, 1-hour, 34-minute period from Monday, 22 March 2021 at 09:56 UTC to Friday, 02 April 2021 at 11:30 UTC.

SAN FRANCISCO, April 02, 2021 (GLOBE NEWSWIRE) -- Holberton, making software engineering education affordable and accessible globally, today announced the appointment of a new Machine Learning and Mathematics Team to build out a comprehensive program to accelerate training students in the key tenets of Artificial Intelligence (AI), the engine of the New Economy. On LinkedIn, there are currently 60,000 machine learning jobs open in the U.S. alone. Many are technology giants such as Twitter and TikTok. But increasingly traditional tech companies are investing in machine learning and recruiting machine learning engineers: even companies like McDonald's. According to LinkedIn, machine learning has created one of the biggest employment opportunities of 2021.

Ontology alignment process is overwhelmingly cited in Knowledge Engineering as a key mechanism aimed at bypassing heterogeneity and reconciling various data sources, represented by ontologies, i.e., the the Semantic Web cornerstone. In such infrastructures and environments, it is inconceivable to assume that all ontologies covering a particular domain of knowledge are aligned in pairs. Moreover, the high performance of alignment approaches is closely related to two factors, i.e., time consumption and machine resource limitations. Thus, good quality alignments are valuable and it would be appropriate to exploit them. Based on this observation, this article introduces a new method of indirect alignment of ontologies in a cross-lingual context. Indeed, the proposed method deals with alignments of multilingual ontologies and implements an indirect ontology alignment strategy based on a composition and reuse of effective direct alignments. The trigger of the proposed method process is based on alignment algebra which governs the semantics composition of relationships and confidence values. The obtained results, after a thorough and detailed experiment are very encouraging and highlight many positive aspects about the new proposed method.

Non-negative matrix and tensor factorisations are a classical tool in machine learning and data science for finding low-dimensional representations of high-dimensional datasets. In applications such as imaging, datasets can often be regarded as distributions in a space with metric structure. In such a setting, a Wasserstein loss function based on optimal transportation theory is a natural choice since it incorporates knowledge about the geometry of the underlying space. We introduce a general mathematical framework for computing non-negative factorisations of matrices and tensors with respect to an optimal transport loss, and derive an efficient method for its solution using a convex dual formulation. We demonstrate the applicability of this approach with several numerical examples.

As algorithmic decision-making systems are becoming more pervasive, it is crucial to ensure such systems do not become mechanisms of unfair discrimination on the basis of gender, race, ethnicity, religion, etc. Moreover, due to the inherent trade-off between fairness measures and accuracy, it is desirable to learn fairness-enhanced models without significantly compromising the accuracy. In this paper, we propose Pareto efficient Fairness (PEF) as a suitable fairness notion for supervised learning, that can ensure the optimal trade-off between overall loss and other fairness criteria. The proposed PEF notion is definition-agnostic, meaning that any well-defined notion of fairness can be reduced to the PEF notion. To efficiently find a PEF classifier, we cast the fairness-enhanced classification as a bilevel optimization problem and propose a gradient-based method that can guarantee the solution belongs to the Pareto frontier with provable guarantees for convex and non-convex objectives. We also generalize the proposed algorithmic solution to extract and trace arbitrary solutions from the Pareto frontier for a given preference over accuracy and fairness measures. This approach is generic and can be generalized to any multicriteria optimization problem to trace points on the Pareto frontier curve, which is interesting by its own right. We empirically demonstrate the effectiveness of the PEF solution and the extracted Pareto frontier on real-world datasets compared to state-of-the-art methods.

Arm introduced the Armv9 architecture in response to the global demand for ubiquitous specialized processing with increasingly capable security and artificial intelligence (AI). Armv9 is the first new Arm architecture in a decade, building on the success of Armv8. The new capabilities in Armv9 are designed to accelerate the move from general-purpose to more specialized compute across every application as AI, the Internet of Things (IoT) and 5G gain momentum globally. To address the greatest technology challenge today – securing the world's data – the Armv9 roadmap introduces the Arm Confidential Compute Architecture (CCA). Confidential computing shields portions of code and data from access or modification while in-use, even from privileged software, by performing computation in a hardware-based secure environment.

Deepfake is the manipulated video made with a generative deep learning technique such as Generative Adversarial Networks (GANs) or Auto Encoder that anyone can utilize. Recently, with the increase of Deepfake videos, some classifiers consisting of the convolutional neural network that can distinguish fake videos as well as deepfake datasets have been actively created. However, the previous studies based on the CNN structure have the problem of not only overfitting, but also considerable misjudging fake video as real ones. In this paper, we propose a Vision Transformer model with distillation methodology for detecting fake videos. We design that a CNN features and patch-based positioning model learns to interact with all positions to find the artifact region for solving false negative problem. Through comparative analysis on Deepfake Detection (DFDC) Dataset, we verify that the proposed scheme with patch embedding as input outperforms the state-of-the-art using the combined CNN features. Without ensemble technique, our model obtains 0.978 of AUC and 91.9 of f1 score, while previous SOTA model yields 0.972 of AUC and 90.6 of f1 score on the same condition.

This article is part of the VB Lab / NVIDIA GTC insight series. "The story of GTC is in many ways the story of NVIDIA, and it's also the story of what's happening in technology," says Greg Estes, VP of corporate marketing and developer programs at NVIDIA. Twelve years ago, GTC began as a conference focused squarely on GPUs, and at that time, that meant primarily graphics and gaming. "But then people figured out that GPUs are the perfect architecture for AI," says Estes. GTC is now billed as the conference for AI innovators, developers, technologists, startups and creatives, and this year it will offer over 1,500 sessions covering breakthroughs in AI, data center, accelerated computing, autonomous vehicles, health care, intelligent networking, game development, and more.

As the U.S. economy rebounds from its pandemic slump, a vital cog is in short supply: the computer chips that power a wide range of products that connect, transport and entertain us in a world increasingly dependent on technology. The shortage has already been rippling through various markets since last summer. It has made it difficult for schools to buy enough laptops for students forced to learn from home, delayed the release of popular products such as the iPhone 12 and created mad scrambles to find the latest video game consoles such as the PlayStation 5. But things have been getting even worse in recent weeks, particularly in the auto industry, where factories are shutting down because there aren't enough chips to finish building vehicles that are starting to look like computers on wheels. The problem was recently compounded by a grounded container ship that blocked the Suez Canal for nearly a week, choking off chips headed from Asia to Europe.