This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is presented and its challenges are investigated. The problem is then tackled by the RL based on DC-OPF (Optimal Power Flow). Designs of the key elements of the RL framework (rewards, states, etc.) are also discussed in detail. Experiments on the IEEE 118-bus system by both shallow and deep neural networks demonstrate promising results in terms of reduced system collapse rates.

The'AI Apocalypse' might kill humanity before any actual robot uprising Education Images/Universal Images Group via Getty Images You can think of artificial intelligence (AI) in the same way you think about cloud computing, if you think about either of them through an environmental lens: an enormous and growing source of carbon emissions, with the very real potential to choke out humans' ability to breathe clean air long before a sentient and ornery AI goes all Skynet on us. At the moment, data centers--the enormous rooms full of stacks and stacks of servers that juggle dank memes, fire tweets, your vitally important Google docs and all the other data that is stored somewhere other than on your phone and in your home computer--use about 2% of the world's electricity. SEE ALSO: Can Giant Snow-Blowing Cannons Save Earth From Climate Change? Of that, servers that run AI--processing all the data and making the decisions and computations that a machine mimicking a human brain must handle in order to achieve "deep learning"--use about 0.1% of the world's electricity, according to a recent MIT Technology Review article. The likelihood that figure will grow, it turns out, is quite good.

DUBAI, UNITED ARAB EMIRATES – Yemen's Houthi movement launched drone attacks on oil facilities in a remote area of Saudi Arabia, the group's Al Masirah TV said Saturday, but there was no immediate confirmation from Saudi authorities or state oil giant Aramco. A Saudi-led coalition is battling the Iran-aligned Houthis to try to restore Yemen's government, which was ousted from power in the capital, Sanaa, by the group in late 2014. The war has been in military stalemate for years. The Houthis have stepped up cross-border missile and drone attacks on Saudi Arabia in recent months. "Ten drones targeted Aramco's Shaybah oilfield and refinery in the first Operation: Balance of Deterrence in the east of the kingdom," the Al Masirah channel reported, citing a Houthi military spokesman.

ABSTRACT The length and time scales of atomistic simulations are limited by the computational cost of the methods used to predict material properties. In recent years there has been great progress in the use of machine learning algorithms to develop fast and accurate interatomic potential models, but it remains a challenge to develop models that generalize well and are fast enough to be used at extreme time and length scales. To address this challenge, we have developed a machine learning algorithm based on symbolic regression in the form of genetic programming that is capable of discovering accurate, computationally efficient manybody potential models. The key to our approach is to explore a hypothesis space of models based on fundamental physical principles and select models within this hypothesis space based on their accuracy, speed, and simplicity. The focus on simplicity reduces the risk of overfitting the training data and increases the chances of discovering a model that generalizes well. Our algorithm was validated by rediscovering an exact Lennard-Jones potential and a Sutton Chen embedded atom method potential from training data generated using these models. By using training data generated from density functional theory calculations, we found potential models for elemental copper that are simple, as fast as embedded atom models, and capable of accurately predicting properties outside of their training set. Our approach requires relatively small sets of training data, making it possible to generate training data using highly accurate methods at a reasonable computational cost. We present our approach, the forms of the discovered models, and assessments of their transferability, accuracy and speed. INTRODUCTION In recent years there have been great advances in the use of machine learning to develop interatomic potential models. Potential models developed in this way are often able to achieve accuracy close to that of the method used to generate the training data, with linear scalability and orders of magnitude increase in performance. Alternatively, potential models may be generated by using fundamental physical relationships to derive a simple parameterized function.

Deep neural networks are known to be fragile to small adversarial perturbations. This issue becomes more critical when a neural network is interconnected with a physical system in a closed loop. In this paper, we show how to combine recent works on neural network certification tools (which are mainly used in static settings such as image classification) with robust control theory to certify a neural network policy in a control loop. Specifically, we give a sufficient condition and an algorithm to ensure that the closed loop state and control constraints are satisfied when the persistent adversarial perturbation is l-infinity norm bounded. Our method is based on finding a positively invariant set of the closed loop dynamical system, and thus we do not require the differentiability or the continuity of the neural network policy. Along with the verification result, we also develop an effective attack strategy for neural network control systems that outperforms exhaustive Monte-Carlo search significantly. We show that our certification algorithm works well on learned models and achieves 5 times better result than the traditional Lipschitz-based method to certify the robustness of a neural network policy on a cart pole control problem.

Japan has told the United States it is ready to provide its robot technology for use in dismantling nuclear and uranium enrichment facilities in North Korea as Washington and Pyongyang pursue further denuclearization talks, government sources said Friday. As Japan turns to the remotely controlled robots it has developed to decommission reactors crippled by the triple core meltdown in 2011 at the Fukushima No. 1 power plant, it believes the same technology can be used in North Korea, according to the sources. The offer is part of Japan's efforts to make its own contribution to the denuclearization talks amid concern that Tokyo could be left out of the loop as the United States and North Korea step up diplomacy. Tokyo has already told Washington it would shoulder part of the costs of any International Atomic Energy Agency inspections of North Korean facilities and dispatch its own nuclear experts to help. The scrapping of nuclear facilities, such as the Yongbyon complex, which has a graphite-moderated reactor, will come into focus in forthcoming working-level talks between Washington and Pyongyang.

A large number of engineering, science and computational problems have yet to be solved in a computationally efficient way. One of the emerging challenges is how evolving technologies grow towards autonomy and intelligent decision making. This leads to collection of large amounts of data from various sensing and measurement technologies, e.g., cameras, smart phones, health sensors, smart electricity meters, and environment sensors. Hence, it is imperative to develop efficient algorithms for generation, analysis, classification, and illustration of data. Meanwhile, data is structured purposefully through different representations, such as large-scale networks and graphs. We focus on data science as a crucial area, specifically focusing on a curse of dimensionality (CoD) which is due to the large amount of generated/sensed/collected data. This motivates researchers to think about optimization and to apply nature-inspired algorithms, such as evolutionary algorithms (EAs) to solve optimization problems. Although these algorithms look un-deterministic, they are robust enough to reach an optimal solution. Researchers do not adopt evolutionary algorithms unless they face a problem which is suffering from placement in local optimal solution, rather than global optimal solution. In this chapter, we first develop a clear and formal definition of the CoD problem, next we focus on feature extraction techniques and categories, then we provide a general overview of meta-heuristic algorithms, its terminology, and desirable properties of evolutionary algorithms.

Early time series classification (eTSC) is the problem of classifying a time series after as few measurements as possible with the highest possible accuracy. The most critical issue of any eTSC method is to decide when enough data of a time series has been seen to take a decision: Waiting for more data points usually makes the classification problem easier but delays the time in which a classification is made; in contrast, earlier classification has to cope with less input data, often leading to inferior accuracy. The state-of-the-art eTSC methods compute a fixed optimal decision time assuming that every times series has the same defined start time (like turning on a machine). However, in many real-life applications measurements start at arbitrary times (like measuring heartbeats of a patient), implying that the best time for taking a decision varies heavily between time series. We present TEASER, a novel algorithm that models eTSC as a two two-tier classification problem: In the first tier, a classifier periodically assesses the incoming time series to compute class probabilities. However, these class probabilities are only used as output label if a second-tier classifier decides that the predicted label is reliable enough, which can happen after a different number of measurements. In an evaluation using 45 benchmark datasets, TEASER is two to three times earlier at predictions than its competitors while reaching the same or an even higher classification accuracy. We further show TEASER's superior performance using real-life use cases, namely energy monitoring, and gait detection.

Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics. However, despite the impressive data-efficiency, MBRL does not achieve the final performance of state-of-the-art Model-free Reinforcement Learning (MFRL) methods. We leverage the strengths of both realms and propose an approach that obtains high performance with a small amount of data. In particular, we combine MFRL and Model Predictive Control (MPC). While MFRL's strength in exploration allows us to train a better forward dynamics model for MPC, MPC improves the performance of the MFRL policy by sampling-based planning. The experimental results in standard continuous control benchmarks show that our approach can achieve MFRL`s level of performance while being as data-efficient as MBRL.

Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unknown parameter vector. As such, the learner is unable to identify all safe actions and must act conservatively in ensuring that her actions satisfy the safety constraint at all rounds (at least with high probability). For these bandits, we propose a new UCB-based algorithm called Safe-LUCB, which includes necessary modifications to respect safety constraints. The algorithm has two phases. During the pure exploration phase the learner chooses her actions at random from a restricted set of safe actions with the goal of learning a good approximation of the entire unknown safe set. Once this goal is achieved, the algorithm begins a safe exploration-exploitation phase where the learner gradually expands their estimate of the set of safe actions while controlling the growth of regret. We provide a general regret bound for the algorithm, as well as a problem dependent bound that is connected to the location of the optimal action within the safe set. We then propose a modified heuristic that exploits our problem dependent analysis to improve the regret.