Convolutional Neural Network (CNN)

Same character, new background, new action. That’s the focus of the latest text-to-image models from Germany’s Black Forest Labs.

Vision transformers have bested convolutional neural networks (CNNs) in a number of key vision tasks. Have CNNs hit their limit? New research suggests otherwise.

A deep learning system detected breast cancer in mammograms as well as experienced radiologists, according to a landmark study.

A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.

A Korean pop star recorded a song in six languages, thanks to deep learning. Midnatt (better known as Lee Hyun) sang his latest release, “Masquerade,” in English, Japanese, Mandarin, Spanish, and Vietnamese — none of which he speaks fluently.

Reinforcement learning agents have mastered games like Go that provide complete information about the state of the game to players. They’ve also excelled at Texas Hold ’Em poker, which provides incomplete information, as few cards are revealed.

A new algorithm defeated a championship-winning Go model using moves that even a middling human player could counter. Researchers trained a model to defeat KataGo, an open source Go-playing system that has beaten top human players.

In spoken conversation, people naturally take turns amid interjections and other patterns that aren’t strictly verbal. A new approach generated natural-sounding audio dialogs without training on text transcriptions that mark when one party should stop speaking and the other should chime in.

Neural networks are making it possible to view parts of the Moon that are perpetually shrouded by darkness. Researchers devised a method called Hyper-effective Noise Removal U-net Software (HORUS) to remove noise from images of the Moon’s south pole.

Vision Transformers (ViTs) are overtaking convolutional neural networks (CNN) in many vision tasks, but procedures for training them are still tailored for CNNs. New research investigated how various training ingredients affect ViT performance.

Researchers at Baidu introduced PP-Matting, an architecture that, given an image, estimates the transparency of pixels surrounding foreground objects to create mattes without requiring additional input.

Convolutional neural networks separate proteins into functional families without considering their shapes.

Let’s get this out of the way: A brain is not a cluster of graphics processing units, and if it were, it would run software far more complex than the typical artificial neural network. Yet neural networks were inspired by the brain’s architecture.

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.

People with certain genetic disorders share common facial features. Doctors are using computer vision to identify such syndromes in children so they can get early treatment.