There has recently been increasing interest, both theoretical and practical, in utilizing tensor networks for the analysis and design of machine learning systems. In particular, a framework has been proposed that can handle both dense data (e.g., standard regression or classification tasks) and sparse data (e.g., recommender systems), unlike support vector machines and traditional deep learning techniques. Namely, it can be interpreted as applying local feature mappings to the data and, through the outer product operator, modelling all interactions of functions of the features; the corresponding weights are represented as a tensor network for computational tractability. In this paper, we derive efficient prediction and learning algorithms for supervised learning with the Canonical Polyadic (CP) decomposition, including suitable regularization and initialization schemes. We empirically demonstrate that the CP-based model performs at least on par with the existing models based on the Tensor Train (TT) decomposition on standard non-sequential tasks, and better on MovieLens 100K. Furthermore, in contrast to previous works which applied two-dimensional local feature maps to the data, we generalize the framework to handle arbitrarily high-dimensional maps, in order to gain a powerful lever on the expressiveness of the model. In order to enhance its stability and generalization capabilities, we propose a normalized version of the feature maps. Our experiments show that this version leads to dramatic improvements over the unnormalized and/or two-dimensional maps, as well as to performance on non-sequential supervised learning tasks that compares favourably with popular models, including neural networks.

Artificial intelligence (AI) has been a topic of major research for many years. Especially, with the emergence of deep neural network (DNN), these studies have been tremendously successful. Today machines are capable of making faster, more accurate decision than human. Thanks to the great development of machine learning (ML) techniques, ML have been used many different fields such as education, medicine, malware detection, autonomous car etc. In spite of having this degree of interest and much successful research, ML models are still vulnerable to adversarial attacks. Attackers can manipulate clean data in order to fool the ML classifiers to achieve their desire target. For instance; a benign sample can be modified as a malicious sample or a malicious one can be altered as benign while this modification can not be recognized by human observer. This can lead to many financial losses, or serious injuries, even deaths. The motivation behind this paper is that we emphasize this issue and want to raise awareness. Therefore, the security gap of mammographic image classifier against adversarial attack is demonstrated. We use mamographic images to train our model then evaluate our model performance in terms of accuracy. Later on, we poison original dataset and generate adversarial samples that missclassified by the model. We then using structural similarity index (SSIM) analyze similarity between clean images and adversarial images. Finally, we show how successful we are to misuse by using different poisoning factors.

Proof assistants offer tactics to facilitate inductive proofs. However, it still requires human ingenuity to decide what arguments to pass to those induction tactics. To automate this process, we present smart_induct for Isabelle/HOL. Given an inductive problem in any problem domain, smart_induct lists promising arguments for the induct tactic without relying on a search. Our evaluation demonstrated smart_induct produces valuable recommendations across problem domains.

The "Hey, Update My Voice" movement, in partnership with UNESCO, was born out of this context with the goal of teaching respect towards virtual assistants and, in addition, asking tech companies to update their assistants' responses. Because if that happens to them, imagine what happens in real life to real women. Every day around the world, virtual assistants suffer abuse and harassment of all kinds. In Brazil, for example, Lu, the virtual assistant of Magazine Luiza stores, has been victimized by this sort of violence. Worldwide, cases have been reported involving Siri and Alexa, among others.

Davos, Switzerland – "Has China Won?" Kishore Mahbubeni, the Singaporean author and intellectual, greets me warmly in a conference lounge here and hands me a card promoting the March release of his new book, bearing that provocative question as its title. The cover blurb announces that he will explain "how, while America became arrogant and distracted, a three-thousand-year-old civilization is well on the way to becoming the number one power in the world." The year ahead is likely to provide the most profound trial yet for that thesis and for the durability of China's rise. Several new shocks and challenges, ranging from a potential pandemic to slowing growth, will test the resilience of China's authoritarian leadership and the state-run capitalist system that has provided the country four decades of record growth. It thus also could mark a significant year for the emerging, generational clash, not of civilizations as Samuel Huntington had argued, but rather of economic and political systems, between democratic and authoritarian capitalism.

We propose a novel neural network architecture, named the Global Workspace Network (GWN), that addresses the challenge of dynamic uncertainties in multimodal data fusion. The GWN is inspired by the well-established Global Workspace Theory from cognitive science. We implement it as a model of attention, between multiple modalities, that evolves through time. The GWN achieved F1 score of 0.92, averaged over two classes, for the discrimination between patient and healthy participants, based on the multimodal EmoPain dataset captured from people with chronic pain and healthy people performing different types of exercise movements in unconstrained settings. In this task, the GWN significantly outperformed a vanilla architecture. It additionally outperformed the vanilla model in further classification of three pain levels for a patient (average F1 score = 0.75) based on the EmoPain dataset. We further provide extensive analysis of the behaviour of GWN and its ability to deal with uncertainty in multimodal data.

Artificial intelligence is gaining traction in areas of social responsibility. From climate change to social polarization to epidemics, humankind has been seeking new solutions to old but persistent problems. From a technological point of view, the amount of daily data produced in the digital universe now allows for state-of-the-art approaches, which may lead to innovative solutions in these underserved areas. AI for social good turned into a reality for us at Tryolabs after we collaborated with an NGO to improve upon how African lions are tracked, which helps with species preservation. We will go into more detail on that timely case, especially as wildlife conservation faces the immense challenges posed by devastating megafires threatening the lives of millions of animals in historic ways.

He uses this tick-tock ratcheting of tension and brief, bright flares of action to move the plot -- an extended, punctuated chase scene that starts early and continues through 400 pages. Verity and Eunice are the rabbit. The hounds are contract assassins, military contractors, tech-bros in over their heads. And Gibson, in his Gibsonian way, just keeps winding the wire around his explosive core, looping in gig-economy surveillance applications, outlaw makers, a barista, a time-traveling robot, a housewarming/launch party complete with helicopter assault.

Airbus will be showcasing their latest secure communications solutions at Intersec this year. Airbus's collaboration tool, Tactilon Agnet will be in the spotlight during the exhibition. The professional solution, which has both application and platform features is used for assisting, for instance, police officers or security personnel. The company will also be showcasing various projects around the use of Artificial Intelligence for mission-critical applications. The latter include facial, license plate, and object recognition, which run on the Tactilon Agnet mission-critical collaborative platform integrated with other systems through Application Programming Interface (APIs) such as Artificial Intelligence services. "Safety and Security is high on the agenda of the UAE Vision 2021, and there is a constant need for safety, security, and mission-critical solutions like the ones presented at this event," commented Andrew Forbes, Head of Middle East and North Africa region for Secure Land Communications at Airbus.

The value of building data-driven businesses with AI at their core is well known today, and business executives are rushing to implement the technology into their operations and gain a competitive advantage, but it's not as simple as creating a data lake and crafting AI models. A large number of AI companies attempting to implement more AI models or build AI-first businesses have experienced challenges. A December 2018 PwC survey found that only 4% of businesses have successfully implemented AI. That's why today the World Economic Forum released the AI toolkit for Boards of Directors. The AI toolkit for Boards of Directors is being released ahead of the annual WEF meeting in Davos, Switzerland where the toolkit will be formally debuted next week.