Mergers of binary neutron stars (BNSs) emit signals in both the gravitational-wave (GW) and electromagnetic (EM) spectra. Famously, the 2017 multi-messenger observation of GW170817 led to scientific discoveries across cosmology, nuclear physics, and gravity. Central to these results were the sky localization and distance obtained from GW data, which, in the case of GW170817, helped to identify the associated EM transient, AT 2017gfo, 11 hours after the GW signal. Fast analysis of GW data is critical for directing time-sensitive EM observations; however, due to challenges arising from the length and complexity of signals, it is often necessary to make approximations that sacrifice accuracy. Here, we develop a machine learning approach that performs complete BNS inference in just one second without making any such approximations. This is enabled by a new method for explicit integration of physical domain knowledge into neural networks. Our approach enhances multi-messenger observations by providing (i) accurate localization even before the merger; (ii) improved localization precision by $\sim30\%$ compared to approximate low-latency methods; and (iii) detailed information on luminosity distance, inclination, and masses, which can be used to prioritize expensive telescope time. Additionally, the flexibility and reduced cost of our method open new opportunities for equation-of-state and waveform systematics studies. Finally, we demonstrate that our method scales to extremely long signals, up to an hour in length, thus serving as a blueprint for data analysis for next-generation ground- and space-based detectors.

Graph Neural Networks (GNNs) have displayed considerable promise in graph representation learning across various applications. The core learning process requires the initialization of model weight matrices within each GNN layer, which is typically accomplished via classic initialization methods such as Xavier initialization. However, these methods were originally motivated to stabilize the variance of hidden embeddings and gradients across layers of Feedforward Neural Networks (FNNs) and Convolutional Neural Networks (CNNs) to avoid vanishing gradients and maintain steady information flow. In contrast, within the GNN context classical initializations disregard the impact of the input graph structure and message passing on variance. In this paper, we analyze the variance of forward and backward propagation across GNN layers and show that the variance instability of GNN initializations comes from the combined effect of the activation function, hidden dimension, graph structure and message passing. To better account for these influence factors, we propose a new initialization method for Variance Instability Reduction within GNN Optimization (Virgo), which naturally tends to equate forward and backward variances across successive layers. We conduct comprehensive experiments on 15 datasets to show that Virgo can lead to superior model performance and more stable variance at initialization on node classification, link prediction and graph classification tasks. Codes are in https://github.com/LspongebobJH/virgo_icml2023.

We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event. Our networks are trained using simulated data, including an estimate of the detector-noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters, and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm -- called "DINGO" -- sets a new standard in fast-and-accurate inference of physical parameters of detected gravitational-wave events, which should enable real-time data analysis without sacrificing accuracy.

Cosmological shock waves are essential to understanding the formation of cosmological structures. To study them, scientists run computationally expensive high-resolution 3D hydrodynamic simulations. Interpreting the simulation results is challenging because the resulting data sets are enormous, and the shock wave surfaces are hard to separate and classify due to their complex morphologies and multiple shock fronts intersecting. We introduce a novel pipeline, Virgo, combining physical motivation, scalability, and probabilistic robustness to tackle this unsolved unsupervised classification problem. To this end, we employ kernel principal component analysis with low-rank matrix approximations to denoise data sets of shocked particles and create labeled subsets. We perform supervised classification to recover full data resolution with stochastic variational deep kernel learning. We evaluate on three state-of-the-art data sets with varying complexity and achieve good results. The proposed pipeline runs automatically, has only a few hyperparameters, and performs well on all tested data sets. Our results are promising for large-scale applications, and we highlight now enabled future scientific work.

People often ask me about the real-life potential for inhumane, merciless systems like Hal 9000 or the Terminator to destroy our society. Growing up in Belgium and away from Hollywood, my initial impressions of robots were not so violent. In retrospect, my early positive affiliations with robots likely fueled my drive to build machines to make our everyday lives more enjoyable. Robots working alongside humans to manage day-to-day mundane tasks was a world I wanted to help create. Now, many years later, after emigrating to the United States, finishing my PhD under Andrew Ng, starting the Berkeley Robot Learning Lab, and co-founding Covariant, I'm convinced that robots are becoming sophisticated enough to be the allies and helpful teammates that I hoped for as a child.

From smart infrastructure grids to bot-authored news reports, algorithms and artificial intelligence capabilities are routinely working behind the scenes in various aspects of our day-to-day lives. COVID-19 only accelerated the adoption of automation across industries and Gartner pegged "smarter, responsible [and] scalable AI" as one of its top 2021 data and analytics tech trends. In this roundup, we've highlighted some of the ways AI is transforming everything from animal conversation efforts to matchmaking in the digital age. The agtech company AppHarvest is using a number of transformative practices to reimagine farming in the 21st century, including AI. The company is tapping computer vision and AI to help its robo-harvester, Virgo, pick ripe produce right from the vine.

From online dating to cybersecurity, AI is routinely working behind the scenes in various aspects of our day-to-day lives. From smart infrastructure grids to bot-authored news reports, algorithms and artificial intelligence capabilities are routinely working behind the scenes in various aspects of our day-to-day lives. COVID-19 only accelerated the adoption of automation across industries and Gartner pegged "smarter, responsible [and] scalable AI" as one of its top 2021 data and analytics tech trends. In this roundup, we've highlighted some of the ways AI is transforming everything from animal conversation efforts to matchmaking in the digital age. The agtech company AppHarvest is using a number of transformative practices to reimagine farming in the 21st century, including AI.

This article was originally published at The Conversation. The publication contributed the article to Space.com's Astronomy is all about data. The universe is getting bigger and so too is the amount of information we have about it. But some of the biggest challenges of the next generation of astronomy lie in just how we're going to study all the data we're collecting.

Root AI, a Somerville, Mass.-based startup developing the Virgo harvesting robot for indoor farms, was acquired by AppHarvest for $60 million. AppHarvest is investing approximately $10 million in cash and the remaining balance in AppHarvest common shares to acquire Root AI. Founded in 2018, Root AI's 19 full-time employees are expected to join AppHarvest's technology group. Root AI co-founder and CEO Josh Lessing will take on the role of CTO for AppHarvest. He will take the lead in continuing to develop the robots and AI capabilities for the network of indoor farms AppHarvest is building.

In recent months, the coronavirus pandemic has highlighted frangibility in the global supply networks; particularly those involved in food security. Hallmarks of digital transformation, automation, and artificial intelligence, are being tapped to create a decentralized 21st century food chain. On Thursday, the agricultural robotics and artificial intelligence company Root AI announced new capabilities to its AI-enhanced robotic harvester as well as investments totaling more than $7 million. Now that the AI-enhanced robotic harvester has demonstrated enhanced dexterity to tackle crops of various shapes and sizes, the technology could help shore up these vulnerabilities. In the past, Root AI has provided glimpses of its robo-harvester, known as Virgo, picking ripe tomatoes off the vine.