Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to solve the exploration-exploitation dilemma. There has been significant recent interest in integrating Bayesian neural networks into Thompson sampling. Most of these methods rely on global variable uncertainty for exploration. In this paper, we propose a new probabilistic modeling framework for Thompson sampling, where local latent variable uncertainty is used to sample the mean reward. Variational inference is used to approximate the posterior of the local variable, and semi-implicit structure is further introduced to enhance its expressiveness. Our experimental results on eight contextual bandits benchmark datasets show that Thompson sampling guided by local uncertainty achieves state-of-the-arts performance while having low computational complexity.

Exciton diffusion plays a vital role in the function of many organic semiconducting opto-electronic devices, where an accurate description requires precise control of heterojunctions. This poses a challenging problem because the parameterization of heterojunctions in high-dimensional random space is far beyond the capability of classical simulation tools. Here, we develop a novel method based on deep neural network to extract a function for exciton diffusion length on surface roughness with high accuracy and unprecedented efficiency, yielding an abundance of information over the entire parameter space. Our method provides a new strategy to analyze the impact of interfacial ordering on exciton diffusion and is expected to assist experimental design with tailored opto-electronic functionalities.

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the uncertainties. This is conceptually similar to heteroscedastic neural networks that produce variance estimates for each prediction, with the key difference that we do not place a Gaussian prior on the predictions. We propose a novel algorithm that performs simultaneous interval estimation for different calibration levels and effectively leverages the intervals to refine the mean estimates. Our results show that, our approach is consistently superior to existing regularization strategies in deep regression models. Finally, we propose to augment partial dependence plots, a model-agnostic interpretability tool, with expected prediction intervals to reveal interesting dependencies between data and the target.

To help them in their decision-making and implementation, the time has come for another IoTSWC (IoT Solutions World Congress), the international flagship event that will bring together more than 350 exhibitors, including the world's leading suppliers of IoT, artificial intelligence and blockchain solutions. A new feature of this year's fair will be a specific area called IoT Solutions.Font, which will provide visibility for start-ups with original and innovative IoT, Artificial Intelligence, and Blockchain based products and services that have already been tested in the market and with potential for internationalisation. This year the following will be on display: an application that measures the driver's behaviour to update the cost of insurance policies; drones, sensors and blockchain that monitor the water quality of the Volga River; an autonomous electric car equipped with a cybersecurity system that blocks attacks that jeopardize the reliability or privacy of the vehicle; a solution to check gas distribution networks, reducing energy losses and preventing fraud, a platform that combines IoT, artificial intelligence and 5G to provide predictive medical care and handle emergencies affecting the elderly and chronically ill; a system to inspect and repair wind farm turbines using drones; artificial intelligence and the cloud; an assembly assistance system which accurately guides the employees of a factory through the different steps to be performed; an application to enable farmers to view the status of their holdings in real time and facilitate their decision-making; and software based on artificial intelligence for submersible pumps used in oil wells. The latter two have their own monographic forums: Blockchain Solutions World (BSW) and AI & Cognitive Systems Forum (AI & CS) with the aim of deepening these two technologies that enhance and reinvent the internet of things capabilities.

Any hardware requires periodic maintenance and it is a lot of money to carry out all the needed maintenance. The heavier the equipment, the more money needed. If we can optimize this, then it will help save a lot of money. This is why Predictive Maintenance is very important. Please watch this video later when available.

Understanding the workings and behaviors of a city requires knowledge of the different processes that allow people and other biological organisms to live and thrive, as well as understanding of their interrelationships--many of which are complicated and have yet to be deeply explored. "Cities are immensely complex, with many facets and interactions within them," said Pete Beckman, a computer scientist at the U.S. Department of Energy's (DOE) Argonne National Laboratory. "For instance, weather influences human movement; air quality affects long-term health; and availability to transportation helps determine opportunities ranging from employment to social interaction. What we need is a new generation of methods and tools that can help us find relationships hidden within the growing volume and diversity of data that are being collected about cities." Central to these methods is machine learning--the increasingly potent process by which computers train to make predictions or determinations from large quantities of data. Machine learning has revolutionized many parts of our lives, from the game of chess to facial recognition systems, and it is now coming to our cities.

A fundamental challenge in artificial intelligence is to build an agent that generalizes and adapts to unseen environments. A common strategy is to build a decoder that takes the context of the unseen new environment as input and generates a policy accordingly. The current paper studies how to build a decoder for the fundamental continuous control task, linear quadratic regulator (LQR), which can model a wide range of real-world physical environments. We present a simple algorithm for this problem, which uses upper confidence bound (UCB) to refine the estimate of the decoder and balance the exploration-exploitation trade-off. Theoretically, our algorithm enjoys a $\widetilde{O}\left(\sqrt{T}\right)$ regret bound in the online setting where $T$ is the number of environments the agent played. This also implies after playing $\widetilde{O}\left(1/\epsilon^2\right)$ environments, the agent is able to transfer the learned knowledge to obtain an $\epsilon$-suboptimal policy for an unseen environment. To our knowledge, this is first provably efficient algorithm to build a decoder in the continuous control setting. While our main focus is theoretical, we also present experiments that demonstrate the effectiveness of our algorithm.

Our research aims at developing intelligent systems to reduce the transportation-related energy expenditure of a large city by influencing individual behavior. We introduce Copter - an intelligent travel assistant that evaluates multi-modal travel alternatives to find a plan that is acceptable to a person given their context and preferences. We propose a formulation for acceptable planning that brings together ideas from AI, machine learning, and economics. This formulation has been incorporated in Copter that produces acceptable plans in real-time. We adopt a novel empirical evaluation framework that combines human decision data with a high fidelity multi-modal transportation simulation to demonstrate a 4% energy reduction and 20% delay reduction in a realistic deployment scenario in Los Angeles, California, USA. This article is part of the special track on AI and Society.

Autonomous Vehicles (AVs) are increasingly embraced around the world to advance smart mobility and more broadly, smart, and sustainable cities. Algorithms form the basis of decision-making in AVs, allowing them to perform driving tasks autonomously, efficiently, and more safely than human drivers and offering various economic, social, and environmental benefits. However, algorithmic decision-making in AVs can also introduce new issues that create new safety risks and perpetuate discrimination. We identify bias, ethics, and perverse incentives as key ethical issues in the AV algorithms' decision-making that can create new safety risks and discriminatory outcomes. Technical issues in the AVs' perception, decision-making and control algorithms, limitations of existing AV testing and verification methods, and cybersecurity vulnerabilities can also undermine the performance of the AV system. This article investigates the ethical and technical concerns surrounding algorithmic decision-making in AVs by exploring how driving decisions can perpetuate discrimination and create new safety risks for the public. We discuss steps taken to address these issues, highlight the existing research gaps and the need to mitigate these issues through the design of AV's algorithms and of policies and regulations to fully realise AVs' benefits for smart and sustainable cities.

Data-driven models analyze power grids under incomplete physical information, and their accuracy has been mostly validated empirically using certain training and testing datasets. This paper explores error bounds for data-driven models under all possible training and testing scenarios, and proposes an evaluation implementation based on Rademacher complexity theory. We answer key questions for data-driven models: how much training data is required to guarantee a certain error bound, and how partial physical knowledge can be utilized to reduce the required amount of data. Our results are crucial for the evaluation and application of data-driven models in power grid analysis. We demonstrate the proposed method by finding generalization error bounds for two applications, i.e. branch flow linearization and external network equivalent under different degrees of physical knowledge. Results identify how the bounds decrease with additional power grid physical knowledge or more training data.