A major wildfire spread through Colorado, and I spent long hours locating shelters, identifying evacuation routes and piecing together satellite imagery. As the Fourmile Canyon Fire devastated areas to the west of Boulder, ultimately destroying 169 homes and causing US$217 million in damage, my biggest concerns were ensuring that people could safely evacuate and first responders had the best chance of keeping the fire at bay. I spent it sitting comfortably in my home in Bloomington, Indiana, a thousand miles away from the action. I was a volunteer, trying to help fire victims. I had created a webpage to aggregate data about the fire, including the location of shelters and the latest predictions of fire spread. I shared it on Twitter in the hope that someone would find it useful; according to the usage statistics, over 40,000 people did.

A Configuration-Space Decomposition Scheme for Learning-based Collision Checking Yiheng Han 1, Wang Zhao 1, Jia Pan 2, Zipeng Y e 1, Ran Yi 1 and Y ong-Jin Liu 1† Abstract -- Motion planning for robots of high degrees-of- freedom (DOFs) is an important problem in robotics with sampling-based methods in configuration space C as one popular solution. Recently, machine learning methods have been introduced into sampling-based motion planning methods, which train a classifier to distinguish collision free subspace from in-collision subspace in C . In this paper, we propose a novel configuration space decomposition method and show two nice properties resulted from this decomposition. Using these two properties, we build a composite classifier that works compatibly with previous machine learning methods by using them as the elementary classifiers. Experimental results are presented, showing that our composite classifier outperforms state-of-the-art single-classifier methods by a large margin. A real application of motion planning in a multi-robot system in plant phenotyping using three UR5 robotic arms is also presented. I. INTRODUCTION Motion planning plays an important role in robotics, which finds a collision-free path to move a robot from a source to a target position.

We present Any-Precision Deep Neural Networks (Any-Precision DNNs), which are trained with a new method that empowers learned DNNs to be flexible in any numerical precision during inference. The same model in runtime can be flexibly and directly set to different bit-width, by truncating the least significant bits, to support dynamic speed and accuracy trade-off. When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision. This nice property facilitates flexible deployment of deep learning models in real-world applications, where in practice trade-offs between model accuracy and runtime efficiency are often sought. Previous literature presents solutions to train models at each individual fixed efficiency/accuracy trade-off point. But how to produce a model flexible in runtime precision is largely unexplored. When the demand of efficiency/accuracy trade-off varies from time to time or even dynamically changes in runtime, it is infeasible to re-train models accordingly, and the storage budget may forbid keeping multiple models. Our proposed framework achieves this flexibility without performance degradation. More importantly, we demonstrate that this achievement is agnostic to model architectures. We experimentally validated our method with different deep network backbones (AlexNet-small, Resnet-20, Resnet-50) on different datasets (SVHN, Cifar-10, ImageNet) and observed consistent results. Code and models will be available at https://github.com/haichaoyu.

A new algorithm is developed to tackle the issue of sampling non-Gaussian model parameter posterior probability distributions that arise from solutions to Bayesian inverse problems. The algorithm aims to mitigate some of the hurdles faced by traditional Markov Chain Monte Carlo (MCMC) samplers, through constructing proposal probability densities that are both, easy to sample and that provide a better approximation to the target density than a simple Gaussian proposal distribution would. To achieve that, a Gaussian proposal distribution is augmented with a Gaussian Process (GP) surface that helps capture non-linearities in the log-likelihood function. In order to train the GP surface, an iterative approach is adopted for the optimal selection of points in parameter space. Optimality is sought by maximizing the information gain of the GP surface using a minimum number of forward model simulation runs. The accuracy of the GP-augmented surface approximation is assessed in two ways. The first consists of comparing predictions obtained from the approximate surface with those obtained through running the actual simulation model at hold-out points in parameter space. The second consists of a measure based on the relative variance of sample weights obtained from sampling the approximate posterior probability distribution of the model parameters. The efficacy of this new algorithm is tested on inferring reaction rate parameters in a 3-node and 6-node network toy problems, which imitate idealized reaction networks in combustion applications.

Personal use of this material is permitted. Abstract--Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters. By detecting load malfunctio n and recommending energy reduction programs, cost-effective n on-intrusive load monitoring provides intelligent demand-si de management for utilities and end users. In this paper, we boost the accuracy of energy disaggregation with a novel neural network structure named scale-and context-aware network, which exploits multi-scale features and contextual inform ation. Specifically, we develop a multi-branch architecture with m ultiple receptive field sizes and branch-wise gates that connect the branches in the sub-networks. We build a self-attention mod ule to facilitate the integration of global context, and we inco rporate an adversarial loss and on-state augmentation to further im prove the model's performance. Extensive simulation results tes ted on open datasets corroborate the merits of the proposed approa ch, which significantly outperforms state-of-the-art methods . Non-intrusive load monitoring (NILM) is the task of estimating the power demand of a specific appliance from the aggregate consumption of a household measured by a single meter [1]. As the task requires breaking down the total energ y consumed by multiple appliances into appliance-level ener gy consumption records, NILM is synonymous with the phrase "energy disaggregation" [2]. A direct benefit of NILM is that energy end-users can acquire appliance-level consump tion feedbacks and optimize their energy consumption behaviour s accordingly. It is estimated that up to 12% residential ener gy saving can be achieved by providing appliance-level feedba ck [3].

There is, alas, no such thing as a free lunch. This simple and obvious truth is invariably forgotten whenever irrational exuberance teams up with digital technology in the latest quest to "change the world". A case in point was the bitcoin frenzy, where one could apparently become insanely rich by "mining" for the elusive coins. All you needed was to get a computer to solve a complicated mathematical puzzle and – lo! – you could earn one bitcoin, which at the height of the frenzy was worth $19,783.06. All you had to do was buy a mining kit (or three) from Amazon, plug it in and become part of the crypto future. The only problem was that mining became progressively more difficult the closer we got to the maximum number of bitcoins set by the scheme and so more and more computing power was required.

A New Biology for a New Century Obstacles to an Exponential Increase in Synthetic Biology Productivity Machine Learning's Predictive Capabilities Machine Learning Needs Automation To Be Truly Effective Predictive Synthetic Biology Will Dramatically Impact Biology and Inspire Computer Science Biology has changed radically in the past two decades, transitioning from a descriptive science into a design science. The discovery of DNA as the repository of genetic information, and of recombinant DNA as an effective way to modify it, has first led into the development of genetic engineering and later the field of synthetic biology. Synthetic biology(1) goes beyond the historical practice of a biological research based on describing and cataloguing (e.g., Linnaean taxonomic classification or phylogenetic tree development), and aims to design biological systems to a given specification (e.g., production of a given amount of a medical drug or targeted invasion of a specific type of cancer cell). This transition into an industrialized synthetic biology is expected to affect most human activities, from improving human health, to producing renewable biofuels to combat climate change.(2) Some examples commercially available now include synthetic leather and spider silk, renewable biodiesel that propels the Rio de Janeiro public bus system, vegan burgers with meat taste, and sustainable skin-rejuvenating cosmetics.

India has become the third-largest startup nation globally. Many of its business-to-consumer (B2C) ventures are known across the world, be it for an e-commerce website, Flipkart or ride-sharing application, Ola. Presently, a wave of business-to-business (B2B) startups in the niche is quietly making a considerable effect comprehensively. Ascending from the roads of common rural areas, they are breaking the unreasonable impediment, worldwide oil and gas majors and enormous producers being their clients. These organizations are exclusively answerable for India's leap forward in the Artificial Intelligence (AI) space.

We introduce a reinforcement learning framework for retail robo-advising. The robo-advisor does not know the investor's risk preference, but learns it over time by observing her portfolio choices in different market environments. We develop an exploration-exploitation algorithm which trades off costly solicitations of portfolio choices by the investor with autonomous trading decisions based on stale estimates of investor's risk aversion. We show that the algorithm's value function converges to the optimal value function of an omniscient robo-advisor over a number of periods that is polynomial in the state and action space. By correcting for the investor's mistakes, the robo-advisor may outperform a stand-alone investor, regardless of the investor's opportunity cost for making portfolio decisions.

Many real-world multi-agent reinforcement learning applications require agents to communicate, assisted by a communication protocol. These applications face a common and critical issue of communication's limited bandwidth that constrains agents' ability to cooperate successfully. In this paper, rather than proposing a fixed communication protocol, we develop an Informative Multi-Agent Communication (IMAC) method to learn efficient communication protocols. Our contributions are threefold. First, we notice a fact that a limited bandwidth translates into a constraint on the communicated message entropy, thus paving the way of controlling the bandwidth. Second, we introduce a customized batch-norm layer, which controls the messages' entropy to simulate the limited bandwidth constraint. Third, we apply the information bottleneck method to discover the optimal communication protocol, which can satisfy a bandwidth constraint via training with the prior distribution in the method. To demonstrate the efficacy of our method, we conduct extensive experiments in various cooperative and competitive multi-agent tasks across two dimensions: the number of agents and different bandwidths. We show that IMAC converges fast, and leads to efficient communication among agents under the limited-bandwidth constraint as compared to many baseline methods.