Machines learning techniques plays a preponderant role in dealing with massive amount of data and are employed in almost every possible domain. Building a high quality machine learning model to be deployed in production is a challenging task, from both, the subject matter experts and the machine learning practitioners. For a broader adoption and scalability of machine learning systems, the construction and configuration of machine learning workflow need to gain in automation. In the last few years, several techniques have been developed in this direction, known as autoML. In this paper, we present a two-stage optimization process to build data pipelines and configure machine learning algorithms. First, we study the impact of data pipelines compared to algorithm configuration in order to show the importance of data preprocessing over hyperparameter tuning. The second part presents policies to efficiently allocate search time between data pipeline construction and algorithm configuration. Those policies are agnostic from the metaoptimizer. Last, we present a metric to determine if a data pipeline is specific or independent from the algorithm, enabling fine-grain pipeline pruning and meta-learning for the coldstart problem.

An agent learning through interactions should balance its action selection process between probing the environment to discover new rewards and using the information acquired in the past to adopt useful behaviour. This trade-off is usually obtained by perturbing either the agent's actions (e.g., e-greedy or Gibbs sampling) or the agent's parameters (e.g., NoisyNet), or by modifying the reward it receives (e.g., exploration bonus, intrinsic motivation, or hand-shaped rewards). Here, we adopt a disruptive but simple and generic perspective, where we explicitly disentangle exploration and exploitation. Different losses are optimized in parallel, one of them coming from the true objective (maximizing cumulative rewards from the environment) and others being related to exploration. Every loss is used in turn to learn a policy that generates transitions, all shared in a single replay buffer. Off-policy methods are then applied to these transitions to optimize each loss. We showcase our approach on a hard-exploration environment, show its sample-efficiency and robustness, and discuss further implications.

We propose a data-driven approach to solve multiscale elliptic PDEs with random coefficients based on the intrinsic low dimension structure of the underlying elliptic differential operators. Our method consists of offline and online stages. At the offline stage, a low dimension space and its basis are extracted from the data to achieve significant dimension reduction in the solution space. At the online stage, the extracted basis will be used to solve a new multiscale elliptic PDE efficiently. The existence of low dimension structure is established by showing the high separability of the underlying Green's functions. Different online construction methods are proposed depending on the problem setup. We provide error analysis based on the sampling error and the truncation threshold in building the data-driven basis. Finally, we present numerical examples to demonstrate the accuracy and efficiency of the proposed method.

Echo state networks are computationally lightweight reservoir models inspired by the random projections observed in cortical circuitry. As interest in reservoir computing has grown, networks have become deeper and more intricate. While these networks are increasingly applied to nontrivial forecasting tasks, there is a need for comprehensive performance analysis of deep reservoirs. In this work, we study the influence of partitioning neurons given a budget and the effect of parallel reservoir pathways across different datasets exhibiting multi-scale and nonlinear dynamics.

Rocky Mountain Power said yesterday that an artificial intelligence (AI) Home Energy Reports solution helped 330,000 of its customers saved over 41 gigawatt-hours (GWhs) of energy since being introduced less than a year ago. The solution produced the savings at an average of approximately four cents per kilowatt hour, a roughly 25 percent cost reduction as compared to conventional Home Energy Reports. "We were searching for the next wave of customer engagement and a way to drive customers toward a digital, two-way dialogue with us," Clay Monroe, director of customer relations for Rocky Mountain Power, said. "With AI reports we are able to quickly shift from conventional methods of reporting, using general peer comparisons, to true energy empowerment with itemized energy bills and personalized savings tips, while at the same time moving customers to digital reports." In 2018, Rocky Mountain Power replaced its existing Home Energy Reports program with AI-powered reports called iHERs. Approximately 330,000 customers in Utah, Idaho, and Wyoming received itemized energy reports for the first time, and more than 50 percent of these customers moved to digital reports with the help of the iHER solution.

We consider filtering in high-dimensional non-Gaussian state-space models with intractable transition kernels, nonlinear and possibly chaotic dynamics, and sparse observations in space and time. We propose a novel filtering methodology that harnesses transportation of measures, convex optimization, and ideas from probabilistic graphical models to yield robust ensemble approximations of the filtering distribution in high dimensions. Our approach can be understood as the natural generalization of the ensemble Kalman filter (EnKF) to nonlinear updates, using stochastic or deterministic couplings. The use of nonlinear updates can reduce the intrinsic bias of the EnKF at a marginal increase in computational cost. We avoid any form of importance sampling and introduce non-Gaussian localization approaches for dimension scalability. Our framework achieves state-of-the-art tracking performance on challenging configurations of the Lorenz-96 model in the chaotic regime.

This paper introduces an improved method of wind power prediction via weather forecast-contextualized Long Short- Term Memory Neural Network (LSTM) models. Wind power and weather forecast data were acquired from open-source databases and combined. However, a generic LSTM model performs poorly on this data, with erratic behavior observed on even low-variance data sections. To address this issue, LSTM modifications were proposed and tested for accuracy through both a Normalized Mean Absolute Error and the Naive Ratio, which is a score introduced by this paper to quantify unwanted "naive" model behavior. Results showed an increase in model accuracy with the addition of weather forecast data to the models, as well as major improvements in performance with some model modifications, which are attributed to the increased contextualization and stability of the new models. These new and improved models have the potential to improve power grid stability and expedite renewable power integration.

We believe that AI will be a force multiplier on technological progress in our increasingly digital, data-driven world. This is because everything around us today, ranging from culture to consumer products, is a product of intelligence. In this report, we set out to capture a snapshot of the exponential progress in AI with a focus on developments in the past 12 months. Consider this report as a compilation of the most interesting things we've seen with a goal of triggering an informed conversation about the state of AI and its implication for the future. This edition builds on the inaugural State of AI Report 2018, which can be found here: www.stateof.ai/2018 We consider the following key dimensions in our report: - Research: Technology breakthroughs and their capabilities.

Broken water pipes can lead to millions of dollars in damages. When it comes to building construction, all sorts of things can go wrong. The most common problem is water damage, according to insurance claim records. "It's the silent killer," says Yaron Dycian, chief product and strategy officer for WINT Water Intelligence. Water is also an increasingly scarce, and valuable, resource – a reality that is not lost on many big companies who are embracing sustainable practices.

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these networks contain a vast amount of unnecessary structure. In this paper, we study the relationship between pruning and interpretability. Namely, we consider the effect of removing unnecessary structure on the number of hidden units that learn disentangled representations of human-recognizable concepts as identified by network dissection. We aim to evaluate how the interpretability of pruned neural networks changes as they are compressed. We find that pruning has no detrimental effect on this measure of interpretability until so few parameters remain that accuracy beings to drop. Resnet-50 models trained on ImageNet maintain the same number of interpretable concepts and units until more than 90% of parameters have been pruned.