In robotics, ergodic control extends the tracking principle by specifying a probability distribution over an area to cover instead of a trajectory to track. The original problem is formulated as a spectral multiscale coverage problem, typically requiring the spatial distribution to be decomposed as Fourier series. This approach does not scale well to control problems requiring exploration in search space of more than 2 dimensions. To address this issue, we propose the use of tensor trains, a recent low-rank tensor decomposition technique from the field of multilinear algebra. The proposed solution is efficient, both computationally and storage-wise, hence making it suitable for its online implementation in robotic systems. The approach is applied to a peg-in-hole insertion task requiring full 6D end-effector poses, implemented with a 7-axis Franka Emika Panda robot. In this experiment, ergodic exploration allows the task to be achieved without requiring the use of force/torque sensors.

Recent years have witnessed significant advances in technologies and services in modern network applications, including smart grid management, wireless communication, cybersecurity as well as multi-agent autonomous systems. Considering the heterogeneous nature of networked entities, emerging network applications call for game-theoretic models and learning-based approaches in order to create distributed network intelligence that responds to uncertainties and disruptions in a dynamic or an adversarial environment. This paper articulates the confluence of networks, games and learning, which establishes a theoretical underpinning for understanding multi-agent decision-making over networks. We provide an selective overview of game-theoretic learning algorithms within the framework of stochastic approximation theory, and associated applications in some representative contexts of modern network systems, such as the next generation wireless communication networks, the smart grid and distributed machine learning. In addition to existing research works on game-theoretic learning over networks, we highlight several new angles and research endeavors on learning in games that are related to recent developments in artificial intelligence. Some of the new angles extrapolate from our own research interests. The overall objective of the paper is to provide the reader a clear picture of the strengths and challenges of adopting game-theoretic learning methods within the context of network systems, and further to identify fruitful future research directions on both theoretical and applied studies.

A new theorem from the field of quantum machine learning has poked a major hole in the accepted understanding about information scrambling. "Our theorem implies that we are not going to be able to use quantum machine learning to learn typical random or chaotic processes, such as black holes. In this sense, it places a fundamental limit on the learnability of unknown processes," said Zoe Holmes, a post-doc at Los Alamos National Laboratory and coauthor of the paper describing the work published today in Physical Review Letters. "Thankfully, because most physically interesting processes are sufficiently simple or structured so that they do not resemble a random process, the results don't condemn quantum machine learning, but rather highlight the importance of understanding its limits," Holmes said. In the classic Hayden-Preskill thought experiment, a fictitious Alice tosses information such as a book into a black hole that scrambles the text. Her companion, Bob, can still retrieve it using entanglement, a unique feature of quantum physics.

Artificial Intelligence has been a growth catalyst to our society and is cosidered across all idustries as a fundamental technology. However, its development has been limited to the signal processing domain that relies on the generated and collected data from other sensors. In recent research, concepts of Digital Artificial Intelligence and Physicial Artifical Intelligence have emerged and this can be considered a big step in the theoretical development of Artifical Intelligence. In this paper we explore the concept of Physicial Artifical Intelligence and propose two subdomains: Integrated Physicial Artifical Intelligence and Distributed Physicial Artifical Intelligence. The paper will also examine the trend and governance of Physicial Artifical Intelligence.

DENVER--(BUSINESS WIRE)--Veritone, Inc. (NASDAQ: VERI), the creator of the world's first operating system for artificial intelligence, aiWARE, today announced that Business Intelligence Group has named Veritone as a winner in the 2021 Artificial Intelligence Excellence Awards for its patented suite of real-time AI-powered Veritone Energy Solutions. Launched in the fall of 2020, Veritone's energy solutions optimize smart grid energy distribution by continuously knowing how much of what type of energy to deliver where, providing grid resilience and autonomous microgrid management when portions of the grid fail, and optimal economic dispatch during normal operations. The solutions deliver supply/demand forecasting, energy smoothing and optimization, DER synchronization and predictive control, energy arbitrage, and smart grid simulation. The solutions collect current weather forecast data, energy demand, and pricing data, and detect the current state and capacity of all energy devices, to intelligently determine the ideal energy supply mix and pricing to meet grid demand, in real time. Utilities and developers can now deliver profitable renewable energy with unparalleled grid efficiency and resiliency.

STOCKHOLM – Silicon Valley leaders tell us that the Fourth Industrial Revolution will bring untold benefits. They say it is already underway and accelerating, powered by artificial intelligence and other technologies, and warn that we will be left eating dust if we don't get with the program. The prevailing consensus among Israelis that Palestinian nationalism had been defeated – and thus that a political solution to the conflict was no longer necessary – lies in tatters. And even as the violence escalates, it has become clear to both sides that the era of glorious wars and victories is over. This upheaval – which also reflects the impact of robotics, bio- and nanotechnology, 5G, and the Internet of Things (IoT) – is a general-purpose revolution.

The Seinfeld idiom, "worlds are colliding," is probably the best description of work in the age of Corona. Pre-pandemic, it was easy to departmentalize one's professional life from one's home existence. Clearly, my dishpan hands have hindered my writing schedule. Thank goodness for the robots in my life, scrubbing and vacuuming my floors; if only they could power themselves with the crumbs they suck up. The World Bank estimates that 3.5 million tons of solid waste is produced by humans everyday, with America accounting for more than 250 million tons a year or over 4 pounds of trash per citizen.

Reservoir computing (RC) offers efficient temporal data processing with a low training cost by separating recurrent neural networks into a fixed network with recurrent connections and a trainable linear network. The quality of the fixed network, called reservoir, is the most important factor that determines the performance of the RC system. In this paper, we investigate the influence of the hierarchical reservoir structure on the properties of the reservoir and the performance of the RC system. Analogous to deep neural networks, stacking sub-reservoirs in series is an efficient way to enhance the nonlinearity of data transformation to high-dimensional space and expand the diversity of temporal information captured by the reservoir. These deep reservoir systems offer better performance when compared to simply increasing the size of the reservoir or the number of sub-reservoirs. Low frequency components are mainly captured by the sub-reservoirs in later stage of the deep reservoir structure, similar to observations that more abstract information can be extracted by layers in the late stage of deep neural networks. When the total size of the reservoir is fixed, tradeoff between the number of sub-reservoirs and the size of each sub-reservoir needs to be carefully considered, due to the degraded ability of individual sub-reservoirs at small sizes.

Many businesses and industries nowadays rely on large quantities of time series data making time series forecasting an important research area. Global forecasting models that are trained across sets of time series have shown a huge potential in providing accurate forecasts compared with the traditional univariate forecasting models that work on isolated series. However, there are currently no comprehensive time series archives for forecasting that contain datasets of time series from similar sources available for the research community to evaluate the performance of new global forecasting algorithms over a wide variety of datasets. In this paper, we present such a comprehensive time series forecasting archive containing 20 publicly available time series datasets from varied domains, with different characteristics in terms of frequency, series lengths, and inclusion of missing values. We also characterise the datasets, and identify similarities and differences among them, by conducting a feature analysis. Furthermore, we present the performance of a set of standard baseline forecasting methods over all datasets across eight error metrics, for the benefit of researchers using the archive to benchmark their forecasting algorithms.

This paper is based on a machine learning project at the Norwegian University of Science and Technology, fall 2020. The project was initiated with a literature review on the latest developments within time-series forecasting methods in the scientific community over the past five years. The paper summarizes the essential aspects of this research. Furthermore, in this paper, we introduce an LSTM cell's architecture, and explain how different components go together to alter the cell's memory and predict the output. Also, the paper provides the necessary formulas and foundations to calculate a forward iteration through an LSTM. Then, the paper refers to some practical applications and research that emphasize the strength and weaknesses of LSTMs, shown within the time-series domain and the natural language processing (NLP) domain. Finally, alternative statistical methods for time series predictions are highlighted, where the paper outline ARIMA and exponential smoothing. Nevertheless, as LSTMs can be viewed as a complex architecture, the paper assumes that the reader has some knowledge of essential machine learning aspects, such as the multi-layer perceptron, activation functions, overfitting, backpropagation, bias, over- and underfitting, and more.