The 20 words defined in this lexicon reflect the ways in which light irradiates the atmosphere, the universe, and our perception of the world. Because no single system--scientific, religious, philosophical, or cultural--can possibly encompass every meaning of light, this lexicon is systematically unsystematic, exploring each of these realms through words that serve as synecdoches for ways in which we understand light and its myriad effects. Each of Earth's poles has an aurora, which can occasionally grow large enough to be seen near the equator, inspiring visions of apocalypse. For the Inuit, who are more accustomed to it, the aurora is perceived as a football game played by spirits in the heavens. The scientific explanation is no less astounding.

"It is now too late to stop a future collapse of our societies because of climate change." These are not the words of a tinfoil hat-donning survivalist. This is from a paper delivered by a senior sustainability academic at a leading business school to the European Commission in Brussels, earlier this year. Before that, he delivered a similar message to a UN conference: "Climate change is now a planetary emergency posing an existential threat to humanity." In the age of climate chaos, the collapse of civilization has moved from being a fringe, taboo issue to a more mainstream concern. As the world reels under each new outbreak of crisis--record heatwaves across the Western hemisphere, devastating fires across the Amazon rainforest, the slow-moving Hurricane Dorian, severe ice melting at the poles--the question of how bad things might get, and how soon, has become increasingly urgent. The fear of collapse is evident in the framing of movements such as'Extinction Rebellion' and in resounding warnings that business-as-usual means heading toward an uninhabitable planet. But a growing number of experts not only point at the looming possibility that human civilization itself is at risk; some believe that the science shows it is already too late to prevent collapse. The outcome of the debate on this is obviously critical: it throws light on whether and how societies should adjust to this uncertain landscape. Yet this is not just a scientific debate. It also raises difficult moral questions about what kind of action is warranted to prepare for, or attempt to avoid, the worst. Scientists may disagree about the timeline of collapse, but many argue that this is entirely beside the point. While scientists and politicians quibble over timelines and half measures, or how bad it'll all be, we are losing precious time.

The Oil & Gas sector is ripe for innovation, particularly when it comes to Artificial Intelligence (AI). A recent report conducted by Markets & Markets suggested that the value of AI within the Oil and Gas industry could reach a monumental $2.85 billion by 2022 – with an astonishing compound annual growth rate (CAGR) of 13%. Right now, the potential application of AI in Oil and Gas is broad and diverse, from process efficiencies and facilities management and safety, to forecasting, planning and surveying. We recently explored how augmented reality (AR) is already revolutionising the oil and gas sector and AR in the new enterprise. One fantastic example of how AI is impacting the Oil and Gas industry is a recent initiative conducted by ExxonMobil.

Running a hotel is demanding, the challenging day-to-day operations can divert your attention away from the bigger picture. That's why in this post we have listed pro-active strategies to implement in your hotel, that will have big results in increasing your revenue. So, without further ado let's dive straight in. Sustainability has emerged as one of the biggest hotel trends back in 2018, and it's gaining traction. Consumers are not only making'greener' choices with the brands they associate themselves with, but it even stretches to their experiences with companies. Did you know a whopping 68% of tourists choose to book with eco-friendly accommodation?

One of the effects of the ongoing trade war between the US and China is likely to be the accelerated development of what are being called "artificial intelligence chips", or AI chips for short, also sometimes referred to as AI accelerators. AI chips could play a critical role in economic growth going forward because they will inevitably feature in cars, which are becoming increasingly autonomous; smart homes, where electronic devices are becoming more intelligent; robotics, obviously; and many other technologies. AI chips, as the term suggests, refers to a new generation of microprocessors which are specifically designed to process artificial intelligence tasks faster, using less power. Obvious, you might think, but some might wonder what the difference between an AI chip and a regular chip would be when all chips of any type process zeros and ones – a typical processor, after all, is actually capable of AI tasks. Graphics-processing units are particularly good at AI-like tasks, which is why they form the basis for many of the AI chips being developed and offered today. Without getting out of our depth, while a general microprocessor is an all-purpose system, AI processors are embedded with logic gates and highly parallel calculation systems that are more suited to typical AI tasks such as image processing, machine vision, machine learning, deep learning, artificial neural networks, and so on. Maybe one could use cars as metaphors. A general microprocessor is your typical family car that might have good speed and steering capabilities.

The diversity of intrinsic qualities of multimedia entities tends to impede their effective retrieval. In a SelfLearning Search Engine architecture, the subtle nuances of human perceptions and deep knowledge are taught and captured through unsupervised reinforcement learning, where the degree of reinforcement may be suitably calibrated. Such architectural paradigm enables indexes to evolve naturally while accommodating the dynamic changes of user interests. It operates by continuously constructing indexes over time, while injecting progressive improvement in search performance. For search operations to be effective, convergence of index learning is of crucial importance to ensure efficiency and robustness. In this paper, we develop a Self-Learning Search Engine architecture based on reinforcement learning using a Markov Decision Process framework. The balance between exploration and exploitation is achieved through evolutionary exploration Strategies. The evolutionary index learning behavior is then studied and formulated using stochastic analysis. Experimental results are presented which corroborate the steady convergence of the index evolution mechanism. Index Term

Multi-agent coordination is prevalent in many real-world applications. However, such coordination is challenging due to its combinatorial nature. An important observation in this regard is that agents in the real world often only directly affect a limited set of neighboring agents. Leveraging such loose couplings among agents is key to making coordination in multi-agent systems feasible. In this work, we focus on learning to coordinate. Specifically, we consider the multi-agent multi-armed bandit framework, in which fully cooperative loosely-coupled agents must learn to coordinate their decisions to optimize a common objective. As opposed to in the planning setting, for learning methods it is challenging to establish theoretical guarantees. We propose multi-agent Thompson sampling (MATS), a new Bayesian exploration-exploitation algorithm that leverages loose couplings. We provide a regret bound that is sublinear in time and low-order polynomial in the highest number of actions of a single agent for sparse coordination graphs. Finally, we empirically show that MATS outperforms the state-of-the-art algorithm, MAUCE, on two synthetic benchmarks, a realistic wind farm control task, and a novel benchmark with Poisson distributions.

Normalization methods such as batch normalization are commonly used in overparametrized models like neural networks. Here, we study the weight normalization (WN) method (Salimans & Kingma, 2016) and a variant called reparametrized projected gradient descent (rPGD) for overparametrized least squares regression and some more general loss functions. WN and rPGD reparametrize the weights with a scale $g$ and a unit vector such that the objective function becomes \emph{non-convex}. We show that this non-convex formulation has beneficial regularization effects compared to gradient descent on the original objective. We show that these methods adaptively regularize the weights and \emph{converge with exponential rate} to the minimum $\ell_2$ norm solution (or close to it) even for initializations \emph{far from zero}. This is different from the behavior of gradient descent, which only converges to the min norm solution when started at zero, and is more sensitive to initialization. Some of our proof techniques are different from many related works; for instance we find explicit invariants along the gradient flow paths. We verify our results experimentally and suggest that there may be a similar phenomenon for nonlinear problems such as matrix sensing.

Despite the availability of ever more data enabled through modern sensor and computer technology, it still remains an open problem to learn dynamical systems in a sample-efficient way. We propose active learning strategies that leverage information-theoretical properties arising naturally during Gaussian process regression, while respecting constraints on the sampling process imposed by the system dynamics. Sample points are selected in regions with high uncertainty, leading to exploratory behavior and data-efficient training of the model. All results are finally verified in an extensive numerical benchmark.

In many settings, as for example wind farms, multiple machines are instantiated to perform the same task, which is called a fleet. The recent advances with respect to the Internet of Things allow control devices and/or machines to connect through cloud-based architectures in order to share information about their status and environment. Such an infrastructure allows seamless data sharing between fleet members, which could greatly improve the sample-efficiency of reinforcement learning techniques. However in practice, these machines, while almost identical in design, have small discrepancies due to production errors or degradation, preventing control algorithms to simply aggregate and employ all fleet data. We propose a novel reinforcement learning method that learns to transfer knowledge between similar fleet members and creates member-specific dynamics models for control. Our algorithm uses Gaussian processes to establish cross-member covariances. This is significantly different from standard transfer learning methods, as the focus is not on sharing information over tasks, but rather over system specifications. We demonstrate our approach on two benchmarks and a realistic wind farm setting. Our method significantly outperforms two baseline approaches, namely individual learning and joint learning where all samples are aggregated, in terms of the median and variance of the results.