Molecular dynamics simulations use statistical mechanics at the atomistic scale to enable both the elucidation of fundamental mechanisms and the engineering of matter for desired tasks. The behavior of molecular systems at the microscale is typically simulated with differential equations parameterized by a Hamiltonian, or energy function. The Hamiltonian describes the state of the system and its interactions with the environment. In order to derive predictive microscopic models, one wishes to infer a molecular Hamiltonian that agrees with observed macroscopic quantities. From the perspective of engineering, one wishes to control the Hamiltonian to achieve desired simulation outcomes and structures, as in self-assembly and optical control, to then realize systems with the desired Hamiltonian in the lab. In both cases, the goal is to modify the Hamiltonian such that emergent properties of the simulated system match a given target. We demonstrate how this can be achieved using differentiable simulations where bulk target observables and simulation outcomes can be analytically differentiated with respect to Hamiltonians, opening up new routes for parameterizing Hamiltonians to infer macroscopic models and develop control protocols.

In this article, we aim at improving the prediction of expert aggregation by using the underlying properties of the models that provide expert predictions. We restrict ourselves to the case where expert predictions come from Kalman recursions, fitting state-space models. By using exponential weights, we construct different algorithms of Kalman recursions Aggregated Online (KAO) that compete with the best expert or the best convex combination of experts in a more or less adaptive way. We improve the existing results on expert aggregation literature when the experts are Kalman recursions by taking advantage of the second-order properties of the Kalman recursions. We apply our approach to Kalman recursions and extend it to the general adversarial expert setting by state-space modeling the errors of the experts. We apply these new algorithms to a real dataset of electricity consumption and show how it can improve forecast performances comparing to other exponentially weighted average procedures.

Neural networks are important tools for data-intensive analysis and are commonly applied to model non-linear relationships between dependent and independent variables. However, neural networks are usually seen as "black boxes" that offer minimal information about how the input variables are used to predict the response in a fitted model. This article describes the \pkg{NeuralSens} package that can be used to perform sensitivity analysis of neural networks using the partial derivatives method. Functions in the package can be used to obtain the sensitivities of the output with respect to the input variables, evaluate variable importance based on sensitivity measures and characterize relationships between input and output variables. Methods to calculate sensitivities are provided for objects from common neural network packages in \proglang{R}, including \pkg{neuralnet}, \pkg{nnet}, \pkg{RSNNS}, \pkg{h2o}, \pkg{neural}, \pkg{forecast} and \pkg{caret}. The article presents an overview of the techniques for obtaining information from neural network models, a theoretical foundation of how are calculated the partial derivatives of the output with respect to the inputs of a multi-layer perceptron model, a description of the package structure and functions, and applied examples to compare \pkg{NeuralSens} functions with analogous functions from other available \proglang{R} packages.

This paper introduces CAAI, a novel cognitive architecture for artificial intelligence in cyber-physical production systems. The goal of the architecture is to reduce the implementation effort for the usage of artificial intelligence algorithms. The core of the CAAI is a cognitive module that processes declarative goals of the user, selects suitable models and algorithms, and creates a configuration for the execution of a processing pipeline on a big data platform. Constant observation and evaluation against performance criteria assess the performance of pipelines for many and varying use cases. Based on these evaluations, the pipelines are automatically adapted if necessary. The modular design with well-defined interfaces enables the reusability and extensibility of pipeline components. A big data platform implements this modular design supported by technologies such as Docker, Kubernetes, and Kafka for virtualization and orchestration of the individual components and their communication. The implementation of the architecture is evaluated using a real-world use case.

Wind-generated electricity has expanded greatly over the past decade. In the U.S., for example, by 2018 wind was generating 6.6% of utility-scale electricity generation, according to the U.S. Energy Information Administration. The criteria for efficient design and reliable operation of the familiar horizontal-axis wind turbines have been well established through decades of experience, leading to ever-larger structures over time, both to intercept more wind and to reach faster winds higher up. As these gargantuan turbines are assembled into large wind farms, often spread over uneven terrain, complex aerodynamic interactions between them have become increasingly important. To address this issue, researchers have proposed protocols that slightly reorient individual turbines to improve the output of others downwind, and they are working with wind farm operators to assess their real-life performance.

Neuromorphic-style inference only works well if limited hardware resources are maximized properly, e.g. accuracy continues to scale with parameters and complexity in the face of potential disturbance. In this work, we use realistic crossbar simulations to highlight that compact implementations of deep neural networks are unexpectedly susceptible to collapse from multiple system disturbances. Our work proposes a middle path towards high performance and strong resilience utilizing the Mosaics framework, and specifically by re-using synaptic connections in a recurrent neural network implementation that possesses a natural form of noise-immunity.

We develop a framework for the adaptive model predictive control of a linear system with unknown parameters and arbitrary bounded costs, in a critical setting where failures are costly and should be prevented at all time. Our approach builds on two ideas: first, we incorporate prior knowledge of the dynamics in the form of a known structure that shapes uncertainty, which can be tightened as we collect interaction data by building high-confidence regions through least-square regression. Second, in order to handle this uncertainty we formulate a robust control objective. Leveraging tools from the interval prediction literature, we convert the confidence regions on parameters into confidence sets on trajectories induced by the controls. These controls are then optimised resorting to tree-based planning methods. We eventually relax our modeling assumptions with a multi-model extension based on a data-driven robust model selection mechanism. The full procedure is designed to produce reasonable and safe behaviours at deployment while recovering an asymptotic optimality. We illustrate it on a practical case of autonomous driving at a crossroads intersection among vehicles with uncertain behaviours.

Gazing up at the night sky in a rural area, you'll probably see the shining moon surrounded by stars. If you're lucky, you might spot the furthest thing visible with the naked eye – the Andromeda galaxy. When the Department of Energy's (DOE) Legacy Survey of Space and Time (LSST) Camera at the National Science Foundation's Vera Rubin Observatory turns on in 2022, it will take photos of 37 billion galaxies and stars over the course of a decade. The output from this huge telescope will swamp researchers with data. In those 10 years, the LSST Camera will take 2,000 photos for each patch of the Southern Sky it covers.

The Canadian artificial intelligence (AI) industry has been growing fast, and the country has been aiming for more through massive AI research. There are signs all over that Canada is already having an AI-driven digital economy as cities are emerging as hubs for AI labs and deep learning research. There is an increase in the number of AI startups in cities such as Montreal, Vancouver, and Toronto, among others. Canada has become a breeding ground for AI innovations. Inc. (NASDAQ: AMZN), Intel Corp (NASDAQ: INTC), and Uber Technologies (NYSE: UBER) have invested significantly in AI research in the country.

A robot dog named'Spot' designed to sniff out bombs went into'sit mode' and refused to move during a live trial by Massachusetts police. Spot was created by Boston Dynamics and was on loan to the bomb squad in 2019 when the failed test happened, according to a report by OneZero. The bomb squad were called to a Walmart in Westboro, Massachusetts after employees spotted a suspicious'old brown briefcase' on a bin in the car park. Officers decided to have Spot examine the briefcase but when they turned him on he went into'sit mode' and wouldn't move - even after multiple reboots. Massachusetts Police were eventually able to get Spot to walk over to the briefcase but the video quality he recorded'wasn't very good' and had to sent a human technician to remove the briefcase - it didn't have a bomb inside.