Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. It can be applied to solve a variety of real-world applications in science and engineering. Bayesian approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc.This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). Then, we outline a few important applications of UQ methods. Finally, we briefly highlight the fundamental research challenges faced by UQ methods and discuss the future research directions in this field.

Greenwaves reveal their latest AI chip, GAP9. Just like the previous generation, it is aimed at AI inferencing in systems at the very edge of the network. Edge computing will increasingly become an integral part of the digital transformation phenomenon. The main benefits deriving from the use of these technologies are the reduction of processing latency, which allows real-time responses, and the saving of bandwidth, sending already processed and, therefore, smaller information to the data center. Compared to GreenWaves Technologies' currently shipping product, GAP8, the latest GAP9 reduces energy consumption by 5 times while enabling inference on neural networks 10 times larger.

Microsoft and the US Department of Energy grabbed headlines by announcing a partnership to develop AI-powered applications to help first responders reacting to natural disasters. One of the first AI prototypes in development will employ computer vision to detect and predict the frontiers of active wildfires and floods. The second application uses an AI tool that should be in every risk manager's toolbox: simulation. This simulator will aid teams in running mock scenarios to better plan and prepare for the next big natural disaster. Many companies were caught flat-footed by COVID-19, perhaps the largest disruption to global trade in a hundred years.

The Knowledge and Intelligence Design section in the Department of Sustainable Design Engineering of the Faculty of Industrial Design Engineering (IDE) offers a PhD position for a duration of four years. The PhD candidate will be supervised by Prof. Alessandro Bozzon. The research work will be conducted in the context of a collaboration between TU Delft, the Amsterdam City Archive, and the CTO Office of Municipality of Amsterdam. The goal is to investigate human-centered artificial intelligence methods for the preservation of large collections of archival documents which are a valuable source of knowledge for cultural, social and urban research of a given city. To fully unlock the knowledge contained in the archives and facilitate the exploration and exploitation of the collections, there is a need for techniques to digitize the archives; to extract structured data, namely Named Entities (NEs) such as persons, locations, events, from unstructured archival documents; and to link the extracted entities to knowledge bases.

The i4 Insight Platform allows shipowners, operators and charterers to access insights on performance and fuel consumption across all ships in their fleet. The addition of GreenSteam's advanced machine learning technology means that platform users will have a more accurate picture of the leading contributors to excessive fuel consumption as well as access to actionable recommendations on how to optimise fleet performance. "Given the sheer volume of performance data available, machine learning is essential to help make sense of complex factors impacting vessel performance to help ensure operational efficiency," a press release from Lloyd's Register stated. GreenSteam was one of the first companies to apply machine learning to vessel performance data and its system can analyse data from thousands of vessels, continually learning, adapting and updating what it knows about each vessel. Shaun Gray, executive chairman of GreenSteam, commented: "An in-depth, data-driven approach to understanding and acting on fuel consumption has never been more necessary for the industry. GreenSteam's machine learning technology uses real ship performance data to provide owners and operators with actionable advice. Unlike traditional analytic approaches that fail to use and model 90% of performance data, by using machine learning, GreenSteam includes all ship performance data in its models to deliver insights other standard methodologies just cannot see."

Artificial intelligence can provide value to natural gas utilities and customers, a National Association of Regulatory Utility Commissioners (NARUC) primer states. The primer from the US regulatory non-profit is aimed to improve awareness of artificial intelligence tools and practices, with a focus on the potential to enhance natural gas utility performance. It zeroes in on the three most common challenges being faced. These are ageing distribution infrastructure, excavator damage to underground infrastructure and customer participation in energy efficiency programmes. Regarding ageing infrastructure, artificial intelligence can assist in identifying and prioritising repair and replacement programmes.

We will show how you can build a diversified portfolio that satisfies specific constraints. For this tutorial, we will build a portfolio that minimizes the risk. So the first thing to do is to get the stock prices programmatically using Python. We will work with the package where you can install it using pip install yfinance --upgrade --no-cache-dir You will need to get the symbol of the stock. You can find the mapping between NASDAQ stocks and symbols in this csv file.

Traffic flow prediction is a crucial task in enabling efficient intelligent transportation systems and smart cities. Although there has been rapid progress in this area in the last few years, given the major advances of deep learning techniques, it remains a challenging task because of the inherent periodic characteristics of traffic flow sequence. To incorporate the periodicity in the prediction process, existing methods have observed three components separately as the input of prediction models, i.e., the closeness, period, and trend components. The long term relation of these components has not been fully addressed. In this paper, we present a novel architecture, TRAILER (TRAnsformer-based tIme-wise Long tErm Relation modeling), to predict traffic flows more effectively. First, we explicitly design a Transformer based long term relation prediction module to model the long term relation and predict the periodic relation to be used for the downstream task. Second, we propose a consistency module at the target time interval, in order to model the consistency of the predicted periodic relation and the relation inferred from the predicted traffic flow tensor. Finally, based on the consistency module, we introduce a consistency loss to stabilize the training process and further improve the prediction performance. Through extensive experiments, we show the superiority of the proposed method on three real-world datasets and the effectiveness of each module in TRAILER.

There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consistently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Motivated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling. We formalize Exploratory Grasping as a Markov Decision Process, study the theoretical complexity of Exploratory Grasping in the context of reinforcement learning and present an efficient bandit-style algorithm, Bandits for Online Rapid Grasp Exploration Strategy (BORGES), which leverages the structure of the problem to efficiently discover high performing grasps for each object stable pose. BORGES can be used to complement any general-purpose grasping algorithm with any grasp modality (parallel-jaw, suction, multi-fingered, etc) to learn policies for objects in which they exhibit persistent failures. Simulation experiments suggest that BORGES can significantly outperform both general-purpose grasping pipelines and two other online learning algorithms and achieves performance within 5% of the optimal policy within 1000 and 8000 timesteps on average across 46 challenging objects from the Dex-Net adversarial and EGAD! object datasets, respectively. Initial physical experiments suggest that BORGES can improve grasp success rate by 45% over a Dex-Net baseline with just 200 grasp attempts in the real world. See https://tinyurl.com/exp-grasping for supplementary material and videos.

Recently it has also become increasingly important in marketing, medicine and political sciences. Process systems engineering community adopts mathematical models successfully in various endeavors such as product and plant design, control system design, operations optimization, etc. (Pantelides and Renfro, 2013; Fung et al., 2016; Safdarnejad et al., 2016). A mathematical model is usually an abstract representation of a true system via sets of equations (algebraic, ordinary differential or partial differential), inequalities (e.g., a range of model validity), and logical conditions. Model development is usually divided into three major steps a) identification of the model structure, b) design and realization of the experiments, and c) estimation of the unknown parameters. In the latter phase, one often realizes maximum-likelihood estimation via least-squares methodology as he/she assumes--knowingly or not--that the measurement error present in the measured data is statistically distributed as a white Gaussian noise. Once the parameter estimates are known, the experimenter commonly determines the quality of the obtained model. This can be done either by using some validation data--if available--or via assessing the joint-confidence regions of the estimated parameters (Beale, 1960; Bates and Watts, 1988; Rooney and Biegler, 2001; Seber and Wild, 2003).