Object detectors typically detect only items that were labeled in their training data. A new method liberates them to locate and recognize a much wider variety of objects.

Getting high accuracy out of a classifier trained on a small number of examples is tricky. You might train the model on several large-scale datasets prior to few-shot training, but what if the few-shot dataset includes novel classes? A new method performs well even in that case.

A neural network wrote the blueprint for upcoming computer chips that will accelerate deep learning itself. Google engineers used a reinforcement learning system to arrange the billions of minuscule transistors in an upcoming version of its Tensor Processing Unit (TPU) chips.

Deploying models for practical use is an industrial concern that generally goes unaddressed in research. As a result, publications on the subject tend to come from the major AI companies.

Craig Wiley has journeyed from the hand-deployed models of yore to the pinnacle of automated AI. Today, as chief product manager of Google Cloud’s AI services, he’s making advanced tools and processes available to anyone with a credit card.

A new study suggests tactics for machine learning engineers to cut their carbon emissions. Led by David Patterson, researchers at Google and UC Berkeley found that AI developers can shrink a model’s carbon footprint a thousand-fold by streamlining architecture...

In some animated games, different characters can perform the same actions — say, walking, jumping, or casting spells. A new system learned from unlabeled data to transfer such motions from one character to another.

Self-attention is a key element in state-of-the-art language models, but it struggles to process images because its memory requirement rises rapidly with the size of the input. New research addresses the issue with a simple twist on a convolutional neural network.

A new system combines verbal descriptions and crude lines to visualize complex scenes. Google researchers led by Jing Yu Koh proposed Tag-Retrieve-Compose-Synthesize (TReCS), a system that generates photorealistic images by describing what they want to see while mousing around on a blank screen.

Smart glasses in the works at Facebook may be equipped with face recognition. The social media colossus plans to market augmented-reality headgear, and it’s considering a feature that would overlay a person’s name on their face.

Having dismissed two key researchers, Google restructured its efforts in AI ethics. Marian Croak, an accomplished software engineer and vice president of engineering at Google, will lead a new center of expertise in responsible AI, the company announced.

AI may help revolutionize the human diet – or dessert, at least. Google applied AI engineer Dale Markowitz and developer advocate Sara Robinson trained a model to predict whether a recipe is...

Performance in language tasks rises with the size of the model — yet, as a model’s parameter count rises, so does the time it takes to render output. New work pumps up the number of parameters without slowing down the network.

The same models trained on the same data may show the same performance in the lab, and yet respond very differently to data they haven’t seen before. New work finds this inconsistency to be pervasive.

How much processing power do various nations have on hand to drive their AI strategy? An international trade group aims to find out. The Organisation for Economic Co-operation and Development (OECD) is launching an effort to measure the computing capacity available in countries around the world.