In many complex planning problems with factored, continuous state and action spaces such as Reservoir Control, Heating Ventilation and Air Conditioning (HVAC), and Navigation domains, it is difficult to obtain a model of the complex nonlinear dynamics that govern state evolution. However, the ubiquity of modern sensors allows us to collect large quantities of data from each of these complex systems and build accurate, nonlinear deep neural network models of their state transitions. But there remains one major problem for the task of control - how can we plan with deep network learned transition models without resorting to Monte Carlo Tree Search and other black-box transition model techniques that ignore model structure and do not easily extend to continuous domains? In this paper, we introduce two types of planning methods that can leverage deep neural network learned transition models: Hybrid Deep MILP Planner (HD-MILP-Plan) and Tensorflow Planner (TF-Plan). In HD-MILP-Plan, we make the critical observation that the Rectified Linear Unit (ReLU) transfer function for deep networks not only allows faster convergence of model learning, but also permits a direct compilation of the deep network transition model to a Mixed-Integer Linear Program (MILP) encoding. Further, we identify deep network specific optimizations for HD-MILP-Plan that improve performance over a base encoding and show that we can plan optimally with respect to the learned deep networks. In TF-Plan, we take advantage of the efficiency of auto-differentiation tools and GPU-based computation where we encode a subclass of purely continuous planning problems as Recurrent Neural Networks and directly optimize the actions through backpropagation. We compare both planners and show that TF-Plan is able to approximate the optimal plans found by HD-MILP-Plan in less computation time. Hence this article offers two novel planners for continuous state and action domains with learned deep neural net transition models: one optimal method (HD-MILP-Plan) and a scalable alternative for large-scale problems (TF-Plan).

Over the past decade terms such as "Data Science", "Big Data", "Data Lake", "Machine Learning", "AI" and so forth have risen to the forefront (and sometimes fallen back again) of the everyday vocabulary used in the widest variety of industries. I do not wish to engage in an extended argument on consistent nomenclature, but there are two frequently used terms that are of particular interest to me: "Data Scientist" and "Machine Learning Engineer". In the broadest possible sense, both of these terms could be understood as referring to "technically skilled people who build machine learning solutions". "Data Scientist" is a term that over the years has become associated with a sort of generalist mathematician or statistician who can also code a bit and knows how to interpret and visualise data. More recently, the term "Machine Learning Engineer" has become associated with software developers who have picked up some mathematics along the way.

Traditional models of weather forecasting are based on statistical measures based on data collected from deep space satellites, such as NOAA's Deep Space Climate Observatory, weather balloons, radar systems, and sometimes from IoT-based sensors. Today, AI is finding a role in weather forecasting with machine learning being employed to process more complex data in less time, with the hope of improving accuracy. For example, the Numerical Weather Prediction (NWP) site from NOAA offers a range of data sets for use by researchers, from temperature and precipitation data to wave heights, according to a recent account in Analytics Insight. The site offers vast data sets relayed from weather satellites, relay stations, and radiosondes to help deliver short-term weather forecasts or long-term climate predictions. Besides machine learning, other AI techniques for weather predictions include Artificial Neural Networks, Ensemble Neural Networks, Backpropagation Networks, Radial Basis Function Networks, General Regression Neural Networks, Genetic Algorithms, Multilayer Perceptrons and fuzzy clustering.

In a world increasingly dominated by AI applications, an understudied aspect is the carbon and social footprint of these power-hungry algorithms that require copious computation and a trove of data for training and prediction. While profitable in the short-term, these practices are unsustainable and socially extractive from both a data-use and energy-use perspective. This work proposes an ESG-inspired framework combining socio-technical measures to build eco-socially responsible AI systems. The framework has four pillars: compute-efficient machine learning, federated learning, data sovereignty, and a LEEDesque certificate. Compute-efficient machine learning is the use of compressed network architectures that show marginal decreases in accuracy. Federated learning augments the first pillar's impact through the use of techniques that distribute computational loads across idle capacity on devices. This is paired with the third pillar of data sovereignty to ensure the privacy of user data via techniques like use-based privacy and differential privacy. The final pillar ties all these factors together and certifies products and services in a standardized manner on their environmental and social impacts, allowing consumers to align their purchase with their values.

To create tomorrow's smarter cities, today's initiatives will need to create measurable improvements. However, a city is a complex system and measuring its performance generates a breadth of issues. Specifically, determining what criteria should be measured, how indications should be defined, and how should the identified indicators be derived. This working paper is one in series that addresses the creation of a Semantic Web based representation of the 17 different themes of ISO 37120 indicators as part of the larger PolisGnosis Project (Fox, 2017). We define a standard ontology for representing general knowledge for the Energy Theme indicators, and for representing both the definition and data used to derive the Energy indicators.

Solving heat transfer equations on chip becomes very critical in the upcoming 5G and AI chip-package-systems. However, batches of simulations have to be performed for data driven supervised machine learning models. Data driven methods are data hungry, to address this, Physics Informed Neural Networks (PINN) have been proposed. However, vanilla PINN models solve one fixed heat equation at a time, so the models have to be retrained for heat equations with different source terms. Additionally, issues related to multi-objective optimization have to be resolved while using PINN to minimize the PDE residual, satisfy boundary conditions and fit the observed data etc. Therefore, this paper investigates an unsupervised learning approach for solving heat transfer equations on chip without using solution data and generalizing the trained network for predicting solutions for heat equations with unseen source terms. Specifically, a hybrid framework of Auto Encoder (AE) and Image Gradient (IG) based network is designed. The AE is used to encode different source terms of the heat equations. The IG based network implements a second order central difference algorithm for structured grids and minimizes the PDE residual. The effectiveness of the designed network is evaluated by solving heat equations for various use cases. It is proved that with limited number of source terms to train the AE network, the framework can not only solve the given heat transfer problems with a single training process, but also make reasonable predictions for unseen cases (heat equations with new source terms) without retraining.

We present a new data-driven model to reconstruct nonlinear flow from spatially sparse observations. The model is a version of a conditional variational auto-encoder (CVAE), which allows for probabilistic reconstruction and thus uncertainty quantification of the prediction. We show that in our model, conditioning on the measurements from the complete flow data leads to a CVAE where only the decoder depends on the measurements. For this reason we call the model as Semi-Conditional Variational Autoencoder (SCVAE). The method, reconstructions and associated uncertainty estimates are illustrated on the velocity data from simulations of 2D flow around a cylinder and bottom currents from the Bergen Ocean Model. The reconstruction errors are compared to those of the Gappy Proper Orthogonal Decomposition (GPOD) method.

We once believed that Macs would never get a virus, closing apps would save battery life, and private mode was really private. For the record, switching to incognito in your browser probably doesn't do what you think. Tap or click for six practical reasons to use it, from keeping your search autofill clean to shopping without spoiling the surprise. And I'm sorry to break it to you, but like a Windows PC, your Mac is certainly at risk. Tap or click for five free downloads that will keep your Mac or PC secure.

Author Summary Recently, quantitative-phase imaging (QPI) has demonstrated the ability to elucidate novel parameters of cellular physiology and metabolism without the need for fluorescent staining. Here, we apply label-free, low photo-toxicity QPI to yeast cells in order to identify lipid droplets (LDs), an important organelle with key implications in human health and biofuel development. Because QPI yields low specificity, we explore the use of modern machine learning methods to rapidly identify intracellular LDs with high discriminatory power and accuracy. In recent years, machine learning has demonstrated exceptional abilities to recognize and segment objects in biomedical imaging, remote sensing, and other areas. Trained machine learning classifiers can be combined with QPI within high-throughput analysis pipelines, allowing for efficient and accurate identification and quantification of cellular components.

A British chip startup has launched what it claims is the world's most complex AI chip, the Colossus MK2 or GC200 IPU (intelligence processing unit). The MK2 and its predecessor MK1 are designed specifically to handle very large machine-learning models. The MK2 processor has 1,472 independent processor cores and 8,832 separate parallel threads, all supported by 900MB of in-processor RAM. Graphcore says the MK2 offers a 9.3-fold improvement in BERT-Large training performance over the MK1, a 8.5-fold improvement in BERT-3Layer inference performance, and a 7.4-fold improvement in EfficientNet-B3 training performance. BERT, or Bidirectional Encoder Representations from Transformers, is a technique for natural language processing pre-training developed by Google for natural language-based searches.