SP Energy Networks is investing in cutting-edge software that applies machine learning algorithms and data science to predict electricity network demand and generation output. The artificial intelligence (AI) forecasting software, which uses historical network data and detailed weather data to make the predictions, will enable the network operator to maximise capacity and reliability across the electricity distribution network. Sia's software will go live in March 2020 and will be used in the real-time management of the network and forward planning when assessing the impact of new connections across the system. The investment comes as Britain's electricity network experiences a rapid transition from fossil fuel generation to renewable energy, low carbon options and energy efficiency programmes. Grant McBeath, Control Room Manager at SP Energy Networks, said: "Demand on the network is forecast to increase considering all future energy scenarios as we transition towards a zero carbon economy. We, therefore, have to change the way we manage the network – transitioning from passive approach to much more active and agile management, which requires a more dynamic approach to ensure capacity is maximised and customers' supplies remain uninterrupted. "Working with Sia on forecasting software will allow us a better understanding of the future flows of energy on the network right down to a half hourly basis.

The simultaneous control of multiple coordinated robotic agents represents an elaborate problem. If solved, however, the interaction between the agents can lead to solutions to sophisticated problems. The concept of swarming, inspired by nature, can be described as the emergence of complex system-level behaviors from the interactions of relatively elementary agents. Due to the effectiveness of solutions found in nature, bio-inspired swarming-based control techniques are receiving a lot of attention in robotics. One method, known as swarm shepherding, is founded on the sheep herding behavior exhibited by sheepdogs, where a swarm of relatively simple agents are governed by a shepherd (or shepherds) which is responsible for high-level guidance and planning. Many studies have been conducted on shepherding as a control technique, ranging from the replication of sheep herding via simulation, to the control of uninhabited vehicles and robots for a variety of applications. We present a comprehensive review of the literature on swarm shepherding to reveal the advantages and potential of the approach to be applied to a plethora of robotic systems in the future.

When and why can a neural network be successfully trained? This article provides an overview of optimization algorithms and theory for training neural networks. First, we discuss the issue of gradient explosion/vanishing and the more general issue of undesirable spectrum, and then discuss practical solutions including careful initialization and normalization methods. Second, we review generic optimization methods used in training neural networks, such as SGD, adaptive gradient methods and distributed methods, and theoretical results for these algorithms. Third, we review existing research on the global issues of neural network training, including results on bad local minima, mode connectivity, lottery ticket hypothesis and infinite-width analysis.

Electrical network frequency (ENF) is the signature of a power distribution grid which represents the nominal frequency (50 or 60 Hz) of a power system network. Due to load variations in a power grid, ENF sequences experience fluctuations. These ENF variations are inherently located in a multimedia signal which is recorded close to the grid or directly from the mains power line. Therefore, a multimedia recording can be localized by analyzing the ENF sequences of that signal in absence of the concurrent power signal. In this paper, a novel approach to analyze location forensics using ENF sequences extracted from a number of power and audio recordings is proposed. The digital recordings are collected from different grid locations around the world. Potential feature components are determined from the ENF sequences. Then, a multi-class support vector machine (SVM) classification model is developed to validate the location authenticity of the recordings. The performance assessments affirm the efficacy of the presented work.

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous interpretation of the training problem as a problem of optimal control, in which neural networks are represented as discretizations of time-dependent ordinary differential equations. A key goal is to develop a method able to intelligently initialize the network parameters for the very deep networks enabled by scalable layer-parallel training. To do this, we apply a refinement strategy across the time domain, that is equivalent to refining in the layer dimension. The resulting refinements create deep networks, with good initializations for the network parameters coming from the coarser trained networks. We investigate the effectiveness of such multilevel "nested iteration" strategies for network training, showing supporting numerical evidence of reduced run time for equivalent accuracy. In addition, we study whether the initialization strategies provide a regularizing effect on the overall training process and reduce sensitivity to hyperparameters and randomness in initial network parameters.

Mean field games (MFG) and mean field control (MFC) are critical classes of multi-agent models for efficient analysis of massive populations of interacting agents. Their areas of application span topics in economics, finance, game theory, industrial engineering, crowd motion, and more. In this paper, we provide a flexible machine learning framework for the numerical solution of potential MFG and MFC models. State-of-the-art numerical methods for solving such problems utilize spatial discretization that leads to a curse-of-dimensionality. We approximately solve high-dimensional problems by combining Lagrangian and Eulerian viewpoints and leveraging recent advances from machine learning. More precisely, we work with a Lagrangian formulation of the problem and enforce the underlying Hamilton-Jacobi-Bellman (HJB) equation that is derived from the Eulerian formulation. Finally, a tailored neural network parameterization of the MFG/MFC solution helps us avoid any spatial discretization. Our numerical results include the approximate solution of 100-dimensional instances of optimal transport and crowd motion problems on a standard work station. These results open the door to much-anticipated applications of MFG and MFC models that were beyond reach with existing numerical methods.

There are over 15 distinct communities that work in the general area of sequential decisions and information, often referred to as decisions under uncertainty or stochastic optimization. We focus on two of the most important fields: stochastic optimal control, with its roots in deterministic optimal control, and reinforcement learning, with its roots in Markov decision processes. Building on prior work, we describe a unified framework that covers all 15 different communities, and note the strong parallels with the modeling framework of stochastic optimal control. By contrast, we make the case that the modeling framework of reinforcement learning, inherited from discrete Markov decision processes, is quite limited. Our framework (and that of stochastic control) is based on the core problem of optimizing over policies. We describe four classes of policies that we claim are universal, and show that each of these two fields have, in their own way, evolved to include examples of each of these four classes.

By Padmaja Ruparel 2019 saw the Indian entrepreneurial ecosystem make a paradigm shift. The country's startup landscape saw the emergence of seven new unicorns and value creation of $90 billion. Little wonder, then, that India is globally ranked third in its number of startups, behind only the US and China. The first half of 2019 saw $3.9 billion invested across 292 domestic investment deals, marking an increase of more than 44% over the same period in 2018. Emerging startups also benefited from the windfall.

Despite its faults and inaccuracies in early iterations, there's no denying that AI is transforming our daily lives at an incredible pace and most of the time the features, and broadly speaking, the benefits it offers are extremely useful. But in terms of its ability to completely transform the energy industry (and specifically oilfield) economics it's important to consider why much of the early AI conversation needs to be tempered with a degree of objectivity. The reality is one of marginal gains in many areas - much like creating a good sports team, over time these gains add up rather than causing instantaneous results everywhere. As a short historical background on AI's components, machine learning was introduced relatively early, when Frank Rosenblatt introduced the first artificial neural network (ANN) in 1958. Two years later Bernard Widrow and Marcian Hoff used this new technology to create MADELINE, an ANN that could eliminate echo in phone lines, which is still in use today.

NNAISENSE has successfully concluded its Series B financing round, with a number of high-profile industrial partners having invested in its vision to integrate True AI into intelligent automation. The company, which draws on more than 25 years of expertise in AI, will apply its state-of-the-art machine learning capabilities to deliver bottom-line improvement to the inspection, modelling, and control of complex industrial production processes. The lead investor in the round is Samsung Ventures Investment Corporation, whose focus is on future-oriented businesses based on new and innovative technologies, while other significant investors include Repsol Energy Ventures SA – the venture capital arm of integrated global energy company Repsol – and Schott AG, who are keen to explore the possibilities AI can deliver as part of its digitalisation program. B2B tech venture fund Alma Mundi Ventures, which was the lead investor in the Series A financing round, increased its position, while Jaan Tallinn's Metaplanet Holdings OÜ also invested further. Tallinn was a founding engineer at Skype and Kazaa and is keen to see AI put to uses that are beneficial and which align with human values.