Given a sequence of numbers, neural networks have proven adept at discovering a mathematical expression that generates it. New work uses transformers to extend that success to a further class of expressions.

When a model trains too much, it can overfit, or memorize, the training data, which reduces its ability to analyze similar-but-different inputs. But what if training continues? New work found that overfitting isn’t the end of the line.

If you buy or sell stocks, it’s handy to test your strategy before you put real money at risk. Researchers devised a fresh approach to simulating market behavior.

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.

A dog doesn’t think twice about fetching a tennis ball, but an autonomous robot typically suffers from delays between perception and action. A new machine-learning model helped a quadruped robot coordinate its sensors and actuators.

A new deep learning technique increased the precision of short-term rainfall forecasts. Researchers developed the Deep Generative Model of Radar (DGMR) to predict amounts of precipitation up to two hours in advance.

Let’s say you have a pretrained language model and a small amount of data to fine-tune it to answer yes-or-no questions. Should you fine-tune it to classify yes/no or to fill in missing words — both viable approaches that are likely to yield different results?

Networked software is often built using a service-oriented architecture, but networked machine learning applications may be easier to manage using a different programming style.

Programming is hard. Programming competitions are harder. Yet transformers proved themselves up to the task.

The higher the accuracy of a pretrained model, the better its performance after fine-tuning, right? Not necessarily. Researchers conducted a meta-analysis of image-recognition experiments and performed some of their own.

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.

Collecting and annotating a dataset of facial portraits is a big job. New research shows that synthetic data can work just as well.

Equipment that relies on computer vision while unplugged — mobile phones, drones, satellites, autonomous cars — need power-efficient models. A new architecture set a record for accuracy per computation.

Visual robots typically perceive the three-dimensional world through sequences of two-dimensional images, but they don’t always know what they’re looking at. For instance, Tesla’s self-driving system has been known to mistake a full moon for a traffic light.

Researchers discovered a new way to reduce memory requirements when training large machine learning models. Tim Dettmers and colleagues at University of Washington released 8-bit optimizers that store gradient statistics as 8-bit values, while maintaining the same accuracy.