Get your team access to 3,500 top Udemy courses anytime, anywhere. Databricks lets you start writing Spark ML code instantly so you can focus on your data problems.

Each summer, high school students are seen in labs across the Georgia Tech Research Institute (GTRI) as part of the STEM@GTRI summer internship program. These students have the opportunity to work on a variety of projects, gaining real-world, hands-on experience from experts currently developing the next personalized technology. Senior Research Scientist Jeff Hurley and Principal Research Engineer Reggie Ratcliff, both housed in the Electronic Systems (ELSYS) Laboratory, hosted four high school students for GTRI's summer program.

The capital of the United Arab Emirates (UAE) has announced the launch of the world's first university dedicated to Artificial Intelligence, in a bid to stay ahead of the disruptive technologies and diversify its economy from the reliance on oil. Named after the Crown Prince of Abu Dhabi and de facto leader of the UAE who has long championed science and technology development in UAE, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) will offer academic post-graduate (MSc and PhD) courses in three key fields of AI – computer vision, machine learning and natural language processing – with access to some of the world's most advanced AI systems to unleash its full potentials. All graduate-level students admitted to the school will be eligible for a full scholarship along with several benefits such as a monthly allowance, accommodation arrangements and health insurance. The first class of graduate students is scheduled to start coursework at MBZUAI campus in Masdar City, a new urban area in Abu Dhabi, in September 2020. "MBZUAI aligns with the vision of the UAE leadership that is based on sustainable development, progress and the overall well-being of humanity and underpinned by capacity-building and active participation in finding practical solutions based on innovation and state-of-the-art technology," said Dr. Sultan Ahmed Al Jaber, UAE Minister of State, who also served as Chair of the university's Board of Trustees, at the press conference in Abu Dhabi.

In the fall of 2017, Sam Bowman, a computational linguist at New York University, figured that computers still weren't very good at understanding the written word. Sure, they had become decent at simulating that understanding in certain narrow domains, like automatic translation or sentiment analysis (for example, determining if a sentence sounds "mean or nice," he said). But Bowman wanted measurable evidence of the genuine article: bona fide, human-style reading comprehension in English. So he came up with a test. In an April 2018 paper coauthored with collaborators from the University of Washington and DeepMind, the Google-owned artificial intelligence company, Bowman introduced a battery of nine reading-comprehension tasks for computers called GLUE (General Language Understanding Evaluation). The test was designed as "a fairly representative sample of what the research community thought were interesting challenges," said Bowman, but also "pretty straightforward for humans." For example, one task asks whether a sentence is true based on information offered in a preceding sentence.

We develop a statistical mechanical approach based on the replica method to study the solution space of deep neural networks. Specifically we analyze the configuration space of the synaptic weights in a simple feed-forward perceptron network within a Gaussian approximation for two scenarios : a setting with random inputs/outputs and a teacher-student setting. By increasing the strength of constraints, i. e. increasing the number of imposed patterns, successive 2nd order glass transition (random inputs/outputs) or 2nd order crystalline transition (teacher-student setting) take place place layer-by-layer starting next to the inputs/outputs boundaries going deeper into the bulk. For deep enough network the central part of the network remains in the liquid phase. We argue that in systems of finite width, weak bias field remain in the central part and plays the role of a symmetry breaking field which connects the opposite sides of the system. In the setting with random inputs/outputs, the successive glass transitions bring about a hierarchical free-energy landscape with ultra-metricity, which evolves in space: it is most complex close to the boundaries but becomes renormalized into progressively simpler one in deeper layers. These observations provide clues to understand why deep neural networks operate efficiently. Finally we present results of a set of numerical simulations to examine the theoretical predictions.

The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from existing tasks for fast learning of future tasks, and online-learning which focuses on the sequential setting in which problems are revealed one by one. In this paper, we generalize the original framework from convex to non-convex setting, and introduce the local regret as the alternative performance measure. We then apply this framework to stochastic settings, and show theoretically that it enjoys a logarithmic local regret, and is robust to any hyperparameter initialization. The empirical test on a real-world task demonstrates its superiority compared with traditional methods.

We investigate online nonlinear regression with long short term memory (LSTM) based networks, which we refer to as LSTM-based online learning. For LSTM-based online learning, we introduce a highly efficient extended Kalman filter (EKF) based training algorithm with a theoretical convergence guarantee. Through simulations, we illustrate significant performance improvements achieved by our algorithm with respect to the conventional LSTM training methods. We particularly show that our algorithm provides very similar error performance with the EKF learning algorithm in 25-40 times shorter training time depending on the parameter size of the network.

Despite the significant advances in recent years, Generative Adversarial Networks (GANs) are still notoriously hard to train. In this paper, we propose three novel curriculum learning strategies for training GANs. All strategies are first based on ranking the training images by their difficulty scores, which are estimated by a state-of-the-art image difficulty predictor. Our first strategy is to divide images into gradually more difficult batches. Our second strategy introduces a novel curriculum loss function for the discriminator that takes into account the difficulty scores of the real images. Our third strategy is based on sampling from an evolving distribution, which favors the easier images during the initial training stages and gradually converges to a uniform distribution, in which samples are equally likely, regardless of difficulty. We compare our curriculum learning strategies with the classic training procedure on two tasks: image generation and image translation. Our experiments indicate that all strategies provide faster convergence and superior results. For example, our best curriculum learning strategy applied on spectrally normalized GANs (SNGANs) fooled human annotators in thinking that generated CIFAR-like images are real in 25.0% of the presented cases, while the SNGANs trained using the classic procedure fooled the annotators in only 18.4% cases. Similarly, in image translation, the human annotators preferred the images produced by the Cycle-consistent GAN (CycleGAN) trained using curriculum learning in 40.5% cases and those produced by CycleGAN based on classic training in only 19.8% cases, 39.7% cases being labeled as ties.

In this paper, we formalise order-robust optimisation as an instance of online learning minimising simple regret, and propose VROOM, a zero'th order optimisation algorithm capable of achieving vanishing regret in non-stationary environments, while recovering favorable rates under stochastic reward-generating processes. Our results are the first to target simple regret definitions in adversarial scenarios unveiling a challenge that has been rarely considered in prior work.

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.