Scientists on Friday said they have developed a simple and inexpensive artificial intelligence (AI) system that can predict when lightning will strike any place within a 30-kilometre radius, up to 30 minutes in advance. Lightning -- one of the most unpredictable phenomena in nature -- regularly kills people and animals and sets fire to homes and forests. It keeps aircraft grounded and damages power lines, wind turbines and solar-panel installations. However, little is known about what triggers lightning, and there is no simple technology for predicting when and where lightning will strike the ground, noted the researchers from Ecole polytechnique federale de Lausanne in Switzerland. The new system, described in the journal Climate and Atmospheric Science, uses a combination of standard meteorological data and artificial intelligence.

Data science has evolved far beyond science. It now represents the heart and soul of many disruptive business applications. Everywhere you look, enterprise data science practices have become industrialized within 24x7 DevOps workflows. Under that trend, automation has come to practically every process in the machine-learning DevOps pipeline that surrounds AI. Modeling is the next and perhaps ultimate milestone in the move toward end-to-end, data-science pipeline automation.

Over the years, Reinforcement Learning (RL) established itself as a convenient paradigm to learn optimal policies from data. However, most RL algorithms achieve optimal policies by exploring all the possible actions and this, in real-world scenarios, is often infeasible or impractical due to e.g. safety constraints. Motivated by this, in this paper we propose to augment RL with Model Predictive Control (MPC), a popular model-based control algorithm that allows to optimally control a system while satisfying a set of constraints. The result is an algorithm, the MPC-augmented RL algorithm (MPCaRL) that makes use of MPC to both drive how RL explores the actions and to modify the corresponding rewards. We demonstrate the effectiveness of the MPCaRL by letting it play against the Atari game Pong. The results obtained highlight the ability of the algorithm to learn general tasks with essentially no training.

Quantum computing exploits basic quantum phenomena such as state superposition and entanglement to perform computations. The Quantum Approximate Optimization Algorithm (QAOA) is arguably one of the leading quantum algorithms that can outperform classical state-of-the-art methods in the near term. QAOA is a hybrid quantum-classical algorithm that combines a parameterized quantum state evolution with a classical optimization routine to approximately solve combinatorial problems. The quality of the solution obtained by QAOA within a fixed budget of calls to the quantum computer depends on the performance of the classical optimization routine used to optimize the variational parameters. In this work, we propose an approach based on reinforcement learning (RL) to train a policy network that can be used to quickly find high-quality variational parameters for unseen combinatorial problem instances. The RL agent is trained on small problem instances which can be simulated on a classical computer, yet the learned RL policy is generalizable and can be used to efficiently solve larger instances. Extensive simulations using the IBM Qiskit Aer quantum circuit simulator demonstrate that our trained RL policy can reduce the optimality gap by a factor up to 8.61 compared with other off-the-shelf optimizers tested.

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal operations. While the control system can compensate for many types of disturbances, there are changes to the process which it still cannot handle adequately. It is therefore important to further develop monitoring systems to effectively detect and identify those faults such that they can be quickly resolved by operators. In this paper, a novel probabilistic fault detection and identification method is proposed which adopts a newly developed deep learning approach using Bayesian recurrent neural networks (BRNNs) with variational dropout. The BRNN model is general and can model complex nonlinear dynamics. Moreover, compared to traditional statistic-based data-driven fault detection and identification methods, the proposed BRNN-based method yields uncertainty estimates which allow for simultaneous fault detection of chemical processes, direct fault identification, and fault propagation analysis. The outstanding performance of this method is demonstrated and contrasted to (dynamic) principal component analysis, which are widely applied in the industry, in the benchmark Tennessee Eastman process (TEP) and a real chemical manufacturing dataset.

Customers expect and use multiple channels to access customer support. "Most customers will still prefer to use an automated or self-service option as long as it is convenient and easy to understand," says Jeff Toister, author of The Service Culture Handbook, "because when a customer does want to connect with a human, it's almost always because something is either urgent or complicated." During the recent California mass power outage everything powered by electricity – Internet Wifi, traffic lights, expresso machines – was brought to a halt. The sheer volume of over 700,000 residents looking for information also brought the PG&E website, chatbots and call centers to their knees. The 2019 CGS Customer Service Chatbot and Channel Survey found that AI technology implementations are happening faster than customers are able, or willing, to embrace them.

A research collaboration between LBNL, PNNL, Brown University, and NVIDIA has achieved exaflop (half-precision) performance on the Summit supercomputer with a deep learning application used to model subsurface flow in the study of nuclear waste remediation. Their achievement, which will be presented during the "Deep Learning on Supercomputers" workshop at SC19, demonstrates the promise of physics-informed generative adversarial networks (GANs) for analyzing complex, large-scale science problems. In science we know the laws of physics and observation principles – mass, momentum, energy, etc.," said George Karniadakis, professor of applied mathematics at Brown and co-author on the SC19 workshop paper. "The concept of physics-informed GANs is to encode prior information from the physics into the neural network. This allows you to go well beyond the training domain, which is very important in applications where the conditions can change." GANs have been applied to model human face ...

The international nuclear arms control regime is approaching a critical juncture. If new nuclear weapons treaties are to be negotiated, ratified and enforced, they will need to be underpinned by strong technical monitoring capabilities. The Department of Energy's National Nuclear Security Administration is leveraging its expertise and technology to meet this challenge, understanding that in nuclear nonproliferation, you can't verify what you can't see. The United States is placing renewed urgency on developing the science and technology required to monitor our adversaries' nuclear activity -- specifically by harnessing the power of artificial intelligence and the unmatched, high-performance computing capabilities found at DOE's national laboratories. DOE houses four of the world's top 10 fastest supercomputers, including the top two, and we are already at work on developing three next-generation, exascale machines, able to conduct a billion billion calculations per second.

Meta-Reinforcement learning approaches aim to develop learning procedures that can adapt quickly to a distribution of tasks with the help of a few examples. Developing efficient exploration strategies capable of finding the most useful samples becomes critical in such settings. Existing approaches towards finding efficient exploration strategies add auxiliary objectives to promote exploration by the pre-update policy, however, this makes the adaptation using a few gradient steps difficult as the pre-update (exploration) and post-update (exploitation) policies are often quite different. Instead, we propose to explicitly model a separate exploration policy for the task distribution. Having two different policies gives more flexibility in training the exploration policy and also makes adaptation to any specific task easier. We show that using self-supervised or supervised learning objectives for adaptation allows for more efficient inner-loop updates and also demonstrate the superior performance of our model compared to prior works in this domain.

Detecting earthquake events from seismic time series has proved itself a challenging task. Manual detection can be expensive and tedious due to the intensive labor and large scale data set. In recent years, automatic detection methods based on machine learning have been developed to improve accuracy and efficiency. However, the accuracy of those methods relies on a sufficient amount of high-quality training data, which itself can be expensive to obtain due to the requirement of domain knowledge and subject matter expertise. This paper is to resolve this dilemma by answering two questions: (1) provided with a limited number of reliable labels, can we use them to generate more synthetic labels; (2) Can we use those synthetic labels to improve the detectability? Among all the existing generative models, the generative adversarial network (GAN) shows its supreme capability in generating high-quality synthetic samples in multiple domains. We designed our model based on GAN. In particular, we studied several different network structures. By comparing the generated results, our GAN-based generative model yields the highest quality. We further combine the dataset with synthetic samples generated by our generative model and show that the detectability of our earthquake classification model is significantly improved than the one trained without augmenting the training set.