Predicting the properties of a molecule from its structure is a challenging task. Recently, deep learning methods have improved the state of the art for this task because of their ability to learn useful features from the given data. By treating molecule structure as graphs, where atoms and bonds are modeled as nodes and edges, graph neural networks (GNNs) have been widely used to predict molecular properties. However, the design and development of GNNs for a given data set rely on labor-intensive design and tuning of the network architectures. Neural architecture search (NAS) is a promising approach to discover high-performing neural network architectures automatically. To that end, we develop an NAS approach to automate the design and development of GNNs for molecular property prediction. Specifically, we focus on automated development of message-passing neural networks (MPNNs) to predict the molecular properties of small molecules in quantum mechanics and physical chemistry data sets from the MoleculeNet benchmark. We demonstrate the superiority of the automatically discovered MPNNs by comparing them with manually designed GNNs from the MoleculeNet benchmark. We study the relative importance of the choices in the MPNN search space, demonstrating that customizing the architecture is critical to enhancing performance in molecular property prediction and that the proposed approach can perform customization automatically with minimal manual effort.

An army of microscopic robots thinner than a human hair have been created that can be injected into the body to wage war on disease, researchers claim. It resembles the plot of sixties film Fantastic Voyage in which a vehicle was injected into a patient. Scientists inside destroyed his blood clot - with a laser gun. The new real-world micro-bots could monitor nerve impulses in the heart or brain, according to scientists from Cornell University who created the machines. The minute four-legged machines will also be able to move through tissue and blood after entering the body via a hypodermic needle.

With a new neural network, lab scientists helped create new formulas that could bridge a power system's static and dynamic features -- a difficult feat. America's power grid system is not only large but dynamic, which makes it especially challenging to manage. Human operators know how to maintain systems when conditions are static.

Ben Lamm is the CEO and founder of US-based advanced technology solutions provider Hypergiant. The Texan serial entrepreneur--it is his fifth company--embarked on his most ambitious enterprise to-date when he co-founded Hypergiant in 2018. Hypergiant is focused on advanced artificial intelligence (AI) for clients in a wide range of range of sectors from oil drilling and fluid dynamics to entertainment and healthcare. It has an impressive roster of industry partners: consultancies Booz Allen Hamilton and EY; applied science company Dynetics; software companies Adobe, Microsoft, AWS and SAP; and computer hardware company Nvidia. Likewise, its clients include leaders in diverse areas of the oil and gas sector including Shell, US E&P independent Marathon Oil, oilfield services company Schlumberger, conglomerate GE and marketing and trading firm Pacific Summit Energy.

In 1959, Nobel laureate and nanotechnology visionary Richard Feynman suggested that it would be interesting to "swallow the surgeon" -- that is, to make a tiny robot that could travel through blood vessels to carry out surgery where needed. This iconic imagining of the future underscored modern hopes for the field of micrometre-scale robotics: to deploy autonomous devices in environments that their macroscopic counterparts cannot reach. However, the construction of such robots presents several challenges, including the obvious difficulty of how to assemble a microscopic locomotive device. In a paper in Nature, Miskin et al.1 report electrochemically driven devices that propel laser-controlled microrobots through a liquid, and which could be easily integrated with microelectronics components to construct fully autonomous microrobots. Designing propulsion strategies for microrobots that move through liquid environments is challenging because strong drag forces prevent microscale objects from maintaining momentum2.

Multi-component polymer systems are of interest in organic photovoltaic and drug delivery applications, among others where diverse morphologies influence performance. An improved understanding of morphology classification, driven by composition-informed prediction tools, will aid polymer engineering practice. We use a modified Cahn-Hilliard model to simulate polymer precipitation. Such physics-based models require high-performance computations that prevent rapid prototyping and iteration in engineering settings. To reduce the required computational costs, we apply machine learning techniques for clustering and consequent prediction of the simulated polymer blend images in conjunction with simulations. Integrating ML and simulations in such a manner reduces the number of simulations needed to map out the morphology of polymer blends as a function of input parameters and also generates a data set which can be used by others to this end. We explore dimensionality reduction, via principal component analysis and autoencoder techniques, and analyse the resulting morphology clusters. Supervised machine learning using Gaussian process classification was subsequently used to predict morphology clusters according to species molar fraction and interaction parameter inputs. Manual pattern clustering yielded the best results, but machine learning techniques were able to predict the morphology of polymer blends with $\geq$ 90 $\%$ accuracy.

Deep neural networks have gained increased attention in machine learning, but they are limited by the fact that many such regression and classification models do not capture prediction uncertainty. Though this might be acceptable for certain non-critical applications, it is not so for oil and gas industry applications where business and economic consequences of wrong or even sub-optimal decision is quite high. In this work I discuss the application of deep neural networks as a framework for approximate Bayesian inference in oilfield reservoir simulation study. Surrogate models with different neural network architecture are proposed to speed up compute- and labor-intensive simulation workflow. Regularization tools such as dropout and batch normalization, variational autoencoder for regression, and probabilistic distribution layers are used to quantify prediction uncertainty. Monte-Carlo dropout approach is further applied to estimate uncertainty given by standard deviation values for the predictions. Probabilistic distribution layers are used to compare its efficacy in capturing the model prediction uncertainty with respect to deterministic neural layers. Deep ensemble approach is also used to train multiple surrogates which capture uncertainty. Among different models tested, VAE based regression model with multivariate-normal latent features works best for prediction uncertainty assessment. Compute time required by surrogate model for prediction is a small fraction of that for full-physics reservoir simulator. Prediction uncertainty information can be used in various simulation workflows to decide when to use surrogate model and when to further explore the solution space using reservoir simulator, thus reducing total computational cost.

The Eulerian fluid simulation is an important HPC application. The neural network has been applied to accelerate it. The current methods that accelerate the fluid simulation with neural networks lack flexibility and generalization. In this paper, we tackle the above limitation and aim to enhance the applicability of neural networks in the Eulerian fluid simulation. We introduce Smartfluidnet, a framework that automates model generation and application. Given an existing neural network as input, Smartfluidnet generates multiple neural networks before the simulation to meet the execution time and simulation quality requirement. During the simulation, Smartfluidnet dynamically switches the neural networks to make the best efforts to reach the user requirement on simulation quality. Evaluating with 20,480 input problems, we show that Smartfluidnet achieves 1.46x and 590x speedup comparing with a state-of-the-art neural network model and the original fluid simulation respectively on an NVIDIA Titan X Pascal GPU, while providing better simulation quality than the state-of-the-art model.

Gennaro discusses the SlothBot, a solar-powered robot that slowly traverses wires, like its animal namesake, to monitor the environment. Gennaro Notomista is a robotics PhD student in the Georgia Robotics and InTelligent Systems Laboratory at Georgia Tech. Gennaro studies control frameworks, with the goal of making robots robust against a changing environment so they can handle long-duration deployments. Toward this goal, he explores constraints-driven control and approaches to coverage control, or enabling robots to traverse closed environments. In addition to the SlothBot, Gennaro has applied his research to areas such as autonomous driving and swarm robotics.

Too many business leaders still believe that AI is just another'plug and play' incremental technological investment. In reality, gaining a competitive advantage through AI requires organizational transformation of the kind exemplified by companies leading in this era: Google, Haier, Apple, Zappos, and Siemens. These companies don't just have better technology -- they have transformed the way they do business so that human resources can be augmented with machine powers. To find out, we conducted a multistage study over five years, beginning with a survey of senior managers and executives, followed by interviews and surveys across a wide range of industries to identify technology implementation strategies and barriers, and in-depth studies of five leading organizations. Our key takeaway is counterintuitive.