Ongoing developments in neural network models are continually advancing the state-of-the-art in terms of system accuracy. However, the predicted labels should not be regarded as the only core output; also important is a well calibrated estimate of the prediction uncertainty. Such estimates and their calibration is critical in relation to robust handling of out of distribution events not observed in training data. Despite their obvious aforementioned advantage in relation to accuracy, contemporary neural networks can, generally, be regarded as poorly calibrated and as such do not produce reliable output probability estimates. Further, while post-processing calibration solutions can be found in the relevant literature, these tend to be for systems performing classification. In this regard, we herein present a method for acquiring calibrated predictions intervals for neural network regressors by posing the regression task as a multi-class classification problem and applying one of three proposed calibration methods on the classifiers' output. Testing our method on two exemplar tasks - speaker age prediction and signal-to-noise ratio estimation - indicates both the suitability of the classification-based regression models and that post-processing by our proposed empirical calibration or temperature scaling methods yields well calibrated prediction intervals. The code for computing calibrated predicted intervals is publicly available.

A San Francisco nonprofit is using a fascinating mix of machine learning and solar panel technology to help the fight against deforestation in Brazil. Rainforest Connection, led by founder and CEO Topher White, creates devices called Guardians that listen to the rainforest and send real-time alerts to combat illegal logging. White's startup places sensors high in the canopy of the Amazon Rainforest in Pará, northern Brazil. The devices are powered by solar panels and built using modified cellphones. Using machine learning and "bio-acoustic monitoring," White analyzes the noises recorded by the sensors, singles out these sounds, and pinpoints the location sent by the Guardian device.

In this work, we study the robust subspace tracking (RST) problem and obtain one of the first two provable guarantees for it. The goal of RST is to track sequentially arriving data vectors that lie in a slowly changing low-dimensional subspace, while being robust to corruption by additive sparse outliers. It can also be interpreted as a dynamic (time-varying) extension of robust PCA (RPCA), with the minor difference that RST also requires a short tracking delay. We develop a recursive projected compressive sensing algorithm that we call Nearly Optimal RST via ReProCS (ReProCS-NORST) because its tracking delay is nearly optimal. We prove that NORST solves both the RST and the dynamic RPCA problems under weakened standard RPCA assumptions, two simple extra assumptions (slow subspace change and most outlier magnitudes lower bounded), and a few minor assumptions. Our guarantee shows that NORST enjoys a near optimal tracking delay of $O(r \log n \log(1/\epsilon))$. Its required delay between subspace change times is the same, and its memory complexity is $n$ times this value. Thus both these are also nearly optimal. Here $n$ is the ambient space dimension, $r$ is the subspaces' dimension, and $\epsilon$ is the tracking accuracy. NORST also has the best outlier tolerance compared with all previous RPCA or RST methods, both theoretically and empirically (including for real videos), without requiring any model on how the outlier support is generated. This is possible because of the extra assumptions it uses.

Derivation of reduced order representations of dynamical systems requires the modeling of the truncated dynamics on the retained dynamics. In its most general form, this so-called closure model has to account for memory effects. In this work, we present a framework of operator inference to extract the governing dynamics of closure from data in a compact, non-Markovian form. We employ sparse polynomial regression and artificial neural networks to extract the underlying operator. For a special class of non-linear systems, observability of the closure in terms of the resolved dynamics is analyzed and theoretical results are presented on the compactness of the memory. The proposed framework is evaluated on examples consisting of linear to nonlinear systems with and without chaotic dynamics, with an emphasis on predictive performance on unseen data.

Last week, telecommunications experts gathered in Barcelona for Mobile World Congress, the industry's premier event and a chance for tech companies to show off their latest innovations in areas as diverse as 5G technology, artificial intelligence, and the cloud. Although the cloud is far from a new idea, its true capabilities are only now beginning to be realized. Here are four ways in which the cloud will shape our lives over the next decade and beyond. Cloud will provide the digital infrastructure of tomorrow's cities, where an estimated 6 billion of the world's population will live by 2045. Smart elevators and parking lots, driverless cars and drone taxis, trains and subways, farms and power plants – all will be safer and better managed, thanks to the cloud's ability to store and analyze data.

Video Friday is your weekly selection of awesome robotics videos, collected by your Automaton bloggers. We'll also be posting a weekly calendar of upcoming robotics events for the next few months; here's what we have so far (send us your events!): Let us know if you have suggestions for next week, and enjoy today's videos. Agility Robotics had a good week. Cassie had a meet-and-greet with a four-legged friend during one of our visits to Playground.

How materials for computer chips, solar panels, and batteries are developed looks to be in the early stages of a radical change. The same goes for research related to areas like superconductors and thermoelectrics. The new possibilities created by machine learning in materials science. "This is something that is set to explode in people's faces, as it were. Within the last five years, there has been a huge growth in materials science research teams using AI/machine learning techniques. The amount of scientific papers on the subject has been growing almost exponentially," says Dr. James Warren, director of the Materials Genome Program in the Material Measurement Laboratory of NIST.

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, and generalization before moving on to more advanced topics in both supervised and unsupervised learning. Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines), and variational methods. Throughout, we emphasize the many natural connections between ML and statistical physics. A notable aspect of the review is the use of Python notebooks to introduce modern ML/statistical packages to readers using physics-inspired datasets (the Ising Model and Monte-Carlo simulations of supersymmetric decays of proton-proton collisions). We conclude with an extended outlook discussing possible uses of machine learning for furthering our understanding of the physical world as well as open problems in ML where physicists maybe able to contribute. (Notebooks are available at https://physics.bu.edu/~pankajm/MLnotebooks.html )

In this paper, we investigate the capability of the universal Kriging (UK) model for single-objective global optimization applied within an efficient global optimization (EGO) framework. We implemented this combined UK-EGO framework and studied four variants of the UK methods, that is, a UK with a first-order polynomial, a UK with a second-order polynomial, a blind Kriging (BK) implementation from the ooDACE toolbox, and a polynomial-chaos Kriging (PCK) implementation. The UK-EGO framework with automatic trend function selection derived from the BK and PCK models works by building a UK surrogate model and then performing optimizations via expected improvement criteria on the Kriging model with the lowest leave-one-out cross-validation error. Next, we studied and compared the UK-EGO variants and standard EGO using five synthetic test functions and one aerodynamic problem. Our results show that the proper choice for the trend function through automatic feature selection can improve the optimization performance of UK-EGO relative to EGO. From our results, we found that PCK-EGO was the best variant, as it had more robust performance as compared to the rest of the UK-EGO schemes; however, total-order expansion should be used to generate the candidate trend function set for high-dimensional problems. Note that, for some test functions, the UK with predetermined polynomial trend functions performed better than that of BK and PCK, indicating that the use of automatic trend function selection does not always lead to the best quality solutions. We also found that although some variants of UK are not as globally accurate as the ordinary Kriging (OK), they can still identify better-optimized solutions due to the addition of the trend function, which helps the optimizer locate the global optimum.

The identification of sources of advection-diffusion transport is based usually on solving complex ill-posed inverse models against the available state- variable data records. However, if there are several sources with different locations and strengths, the data records represent mixtures rather than the separate influences of the original sources. Importantly, the number of these original release sources is typically unknown, which hinders reliability of the classical inverse-model analyses. To address this challenge, we present here a novel hybrid method for identification of the unknown number of release sources. Our hybrid method, called HNMF, couples unsupervised learning based on Nonnegative Matrix Factorization (NMF) and inverse-analysis Green functions method. HNMF synergistically performs decomposition of the recorded mixtures, finds the number of the unknown sources and uses the Green function of advection-diffusion equation to identify their characteristics. In the paper, we introduce the method and demonstrate that it is capable of identifying the advection velocity and dispersivity of the medium as well as the unknown number, locations, and properties of various sets of synthetic release sources with different space and time dependencies, based only on the recorded data. HNMF can be applied directly to any problem controlled by a partial-differential parabolic equation where mixtures of an unknown number of sources are measured at multiple locations.