Even though "de-identified," patient data can still sometimes be revealed by attackers. The focus of this program will include technical and policy measures that might better protect the privacy of electronic health records (EHRs) when they are used for machine learning. The approach to be discussed includes multivariate models computed in a decentralized fashion for a large clinical data research network, and how to collaborate in developing sound methods to protect patient privacy. Sharing according to patient instructions is one important way to conduct responsible machine learning. This presentation will include results from a recent study on patient-controlled electronic healthcare data sharing.

In a brightly coloured shipping container in east London, Rubens Filho is asking me to pick a card. "Any card," he says, fanning the pack out face down. "And don't worry, you can show me. I pull out the seven of spades, and show it to him; he gets me to sign my name on it with a marker pen. Then he slides it back into the middle of the pack, puts the cards back into their box and puts the box on the table in front of us. "Now," he says with a grin, "the magic begins." Filho is 51, tall, handsome and infectiously enthusiastic about the power of magic tricks and illusions. Born in Brazil, he's been a keen magician since adolescence. He came to Britain in 2012 to work in advertising, before, in 2015, setting up Abracademy, a startup dedicated to bringing magic – and in particular the skills needed to perform it – to the rest of us. "I think magic has a such a positive twist," he says. "It brings this soft approach that's hard to explain, this role of creating something beautiful." But he is also fascinated by the relationship between magic and neuroscience and psychology, and set up Abracademy Labs, an offshoot of Abracademy, to explore this connection. "Magic has lived in the'glitches' of the brain for a long time," he says. "How you see things, how you form beliefs, how you experience wonder.

Newswire) GBT Technologies Inc. (OTCPINK: GTCH) ("GBT", or the "Company"), a company specializing in the development of Internet of Things (IoT) and Artificial Intelligence (AI) enabled networking and tracking technologies, including its GopherInsight wireless mesh network technology platform and its Avant! AI, for both mobile and fixed solutions, announced that it is now adding the first elements of cognitive features within its AI expert agent. The agent now includes feedback features, i.e. "thumbs up" and "thumbs down", that work with the artificial neural network mechanism to learn and improve answers' accuracy and their relationship to the topic. The user feedback is fed into the Avant! RNN (Recurrent Neural Network), which synthesizes data from various information sources, weighing and comparing the feedback to the answer context to provide the best, most accurate answers.

Working in information technology is only great up until you decide to stop. While actively working in the business, you're constantly exposed to the latest and greatest tools of the trade. Leave that domain, and suddenly you're completely lost as to what's hot and what's not. Maybe it's not even called information technology anymore (it isn't), but if you worked in that capacity back when the term was relevant, you'll know how to use structured query language (SQL). It's how we can ask relational databases questions.

Recent work has shown how to embed differentiable optimization problems (that is, problems whose solutions can be backpropagated through) as layers within deep learning architectures. This method provides a useful inductive bias for certain problems, but existing software for differentiable optimization layers is rigid and difficult to apply to new settings. In this paper, we propose an approach to differentiating through disciplined convex programs, a subclass of convex optimization problems used by domain-specific languages (DSLs) for convex optimization. We introduce disciplined parametrized programming, a subset of disciplined convex programming, and we show that every disciplined parametrized program can be represented as the composition of an affine map from parameters to problem data, a solver, and an affine map from the solver's solution to a solution of the original problem (a new form we refer to as affine-solver-affine form). We then demonstrate how to efficiently differentiate through each of these components, allowing for end-to-end analytical differentiation through the entire convex program. We implement our methodology in version 1.1 of CVXPY, a popular Python-embedded DSL for convex optimization, and additionally implement differentiable layers for disciplined convex programs in PyTorch and TensorFlow 2.0. Our implementation significantly lowers the barrier to using convex optimization problems in differentiable programs. We present applications in linear machine learning models and in stochastic control, and we show that our layer is competitive (in execution time) compared to specialized differentiable solvers from past work.

This paper tackles the challenge presented by small-data to the task of Bayesian inference. A novel methodology, based on manifold learning and manifold sampling, is proposed for solving this computational statistics problem under the following assumptions: 1) neither the prior model nor the likelihood function are Gaussian and neither can be approximated by a Gaussian measure; 2) the number of functional input (system parameters) and functional output (quantity of interest) can be large; 3) the number of available realizations of the prior model is small, leading to the small-data challenge typically associated with expensive numerical simulations; the number of experimental realizations is also small; 4) the number of the posterior realizations required for decision is much larger than the available initial dataset. The method and its mathematical aspects are detailed. Three applications are presented for validation: The first two involve mathematical constructions aimed to develop intuition around the method and to explore its performance. The third example aims to demonstrate the operational value of the method using a more complex application related to the statistical inverse identification of the non-Gaussian matrix-valued random elasticity field of a damaged biological tissue (osteoporosis in a cortical bone) using ultrasonic waves.

In the geophysical field, seismic noise attenuation has been considered as a critical and long-standing problem, especially for the pre-stack data processing. Here, we propose a model to leverage the deep-learning model for this task. Rather than directly applying an existing de-noising model from ordinary images to the seismic data, we have designed a particular deep-learning model, based on residual neural networks. It is named as N2N-Seismic, which has a strong ability to recover the seismic signals back to intact condition with the preservation of primary signals. The proposed model, achieving with great success in attenuating noise, has been tested on two different seismic datasets. Several metrics show that our method outperforms conventional approaches in terms of Signal-to-Noise-Ratio, Mean-Squared-Error, Phase Spectrum, etc. Moreover, robust tests in terms of effectively removing random noise from any dataset with strong and weak noises have been extensively scrutinized in making sure that the proposed model is able to maintain a good level of adaptation while dealing with large variations of noise characteristics and intensities.

This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with an unseen environment from the same distribution, the policy aims to generalize the exploration strategy to visit the maximum number of unique states in a limited number of steps. We particularly focus on environments with graph-structured state-spaces that are encountered in many important real-world applications like software testing and map building. We formulate this task as a reinforcement learning problem where the `exploration' agent is rewarded for transitioning to previously unseen environment states and employ a graph-structured memory to encode the agent's past trajectory. Experimental results demonstrate that our approach is extremely effective for exploration of spatial maps; and when applied on the challenging problems of coverage-guided software-testing of domain-specific programs and real-world mobile applications, it outperforms methods that have been hand-engineered by human experts.

--Uncertainty quantification for forward and inverse problems is a central challenge across physical and biomedical disciplines. We address this challenge for the problem of modeling subsurface flow at the Hanford Site by combining stochastic computational models with observational data using physics-informed GAN models. The geographic extent, spatial heterogeneity, and multiple correlation length scales of the Hanford Site require training a computationally intensive GAN model to thousands of dimensions. We develop a hierarchical scheme for exploiting domain parallelism, map discriminators and generators to multiple GPUs, and employ efficient communication schemes to ensure training stability and convergence. We developed a highly optimized implementation of this scheme that scales to 27,500 NVIDIA V olta GPUs and 4584 nodes on the Summit supercomputer with a 93.1% scaling efficiency, achieving peak and sustained half-precision rates of 1228 PF/s and 1207 PF/s. Index T erms --Stochastic PDEs, GANs, Deep Learning I. O VERVIEW A. Parameter estimation and uncertainty quantification for subsurface flow models Mathematical models of subsurface flow and transport are inherently uncertain because of the lack of data about the distribution of geological units, the distribution of hydrological properties (e.g., hydraulic conductivity) within each unit, and initial and boundary conditions. Here, we focus on parameter-ization and uncertainty quantification (UQ) in the subsurface flow model at the Department of Energy's Hanford Site, one of the most contaminated sites in the western hemisphere. During the Hanford Site's 60-plus years history, there have been more than 1000 individual sources of contaminants distributed over 200 square miles mostly along Columbia River [1]. Accurate subsurface flow models with rigorous UQ are necessary for assessing risks of the contaminants reaching the Columbia river and numerous wells used by agriculture and as sources of drinking water, as well as for the design of efficient remediation strategies. B. UQ with Stochastic Partial Differential Equations Uncertain initial and boundary conditions and model parameters render the governing model equations stochastic. In this context, UQ becomes equivalent to solving stochastic PDEs (SPDEs). Forward solution of SPDEs requires that all model parameters as well as the initial/boundary conditions are prescribed either deterministically or stochastically, which is not possible unless experimental data are available to provide additional information for critical parameters, e.g. the field conductivity.

Bayesian optimization has recently emerged as a popular method for the sample-efficient optimization of expensive black-box functions. However, the application to high-dimensional problems with several thousand observations remains challenging, and on difficult problems Bayesian optimization is often not competitive with other paradigms. In this paper we take the view that this is due to the implicit homogeneity of the global probabilistic models and an overemphasized exploration that results from global acquisition. This motivates the design of a local probabilistic approach for global optimization of large-scale high-dimensional problems. We propose the $\texttt{TuRBO}$ algorithm that fits a collection of local models and performs a principled global allocation of samples across these models via an implicit bandit approach. A comprehensive evaluation demonstrates that $\texttt{TuRBO}$ outperforms state-of-the-art methods from machine learning and operations research on problems spanning reinforcement learning, robotics, and the natural sciences.