Graph Neural Networks (GNN)

Researchers proposed a way for robots to find objects in households where things get moved around. Andrey Kurenkov and colleagues at Stanford University introduced Node Edge Predictor, a model that learned to predict where objects were located in houses.

Machine learning models have predicted weather a few days ahead of time. A new approach substantially extends the time horizon. Remi Lam and colleagues at Google developed GraphCast, a weather-forecasting system based on graph neural networks (GNNs).

The authors trained a modified GNN on a dataset of 18 million molecules to find molecular properties.

Transformers can learn a lot from sequential data like words in a book, but they’ve shown limited ability to learn from data in the form of a graph. A new transformer variant gives graphs due attention.

Engineers who design aircraft, aqueducts, and other objects that interact with air and water use numerical simulations to test potential shapes, but they rely on trial and error to improve their designs. A neural simulator can optimize the shape itself.

When you’re training a neural network, it takes a lot of computation to optimize its weights using an iterative algorithm like stochastic gradient descent. Wouldn’t it be great to compute the best parameter values in one pass? A new method takes a substantial step in that direction.

Most U.S. state agencies use AI without limits or oversight. An investigative report probed reasons why efforts to rein them in have made little headway. Since 2018, nearly every proposed bill aimed at studying or controlling how state agencies use automated decision systems.

New research shows that drastically increasing the number of layers in a graph neural networks improves its performance on large datasets.

Many medical drugs work by modulating the body’s production of specific proteins. Recent research aimed to predict this activity, enabling researchers to identify drugs that might counteract the effects of Covid-19.

Are your scientist friends intimidated by machine learning? They might be inspired by a primer from one of the world’s premier tech titans. Former Google CEO Eric Schmidt and Cornell PhD candidate Maithra Raghu school scientists in machine learning in a sprawling overview.

Chemists typically develop new antibiotics by testing close chemical relatives of tried-and-true compounds like penicillin. That approach becomes less effective, though, as dangerous bacteria evolve resistance to those very chemical structures. Instead, researchers enlisted neural networks.

Predicting a molecule’s aroma is hard because slight changes in structure lead to huge shifts in perception. Good thing deep learning is developing a sense of smell.