It’s expensive to pay doctors to label medical images, and the relative scarcity of high-quality training examples can make it hard for neural networks to learn features that make for accurate diagnoses.

According to the lottery ticket hypothesis, the bigger the neural network, the more likely some of its weights are initialized to values that are well suited to learning to perform the task at hand. But just how big does it need to be?

How does a convolutional neural network recognize a photo of a ski resort? New research shows that it bases its classification on specific neurons that recognize snow, mountains, trees, and houses.

Recognizing actions performed in a video requires understanding each frame and relationships between the frames. Previous research devised a way to analyze individual images efficiently known as Active Shift Layer (ASL). New research extends this technique to the steady march of video frames.

Trying on new makeup is a hassle — apply, inspect, wash off, repeat. Not to mention the tribulation of visiting brick-and-mortar stores during the pandemic. Augmented reality is helping people try on all the makeup they want without leaving home.

GANs are adept at mapping the artistic style of one picture onto the subject of another, known as style transfer. However, applied to the fanciful illustrations in children’s books, some GANs prove better at preserving style, others better at preserving subject matter.

Convolutional neural networks are good at recognizing disease symptoms in medical scans of patients who were injected with iodine-based dye, that makes their organs more visible. But some patients can’t take the dye. Now synthetic scans from a GAN are helping CNNs learn to analyze undyed images.

Deepfakes have gone mainstream, allowing celebrities to star in commercials without setting foot in a film studio. A new method helps determine whether such endorsements — and other images produced by generative adversarial networks — are authentic.

The technique known as dropout discourages neural networks from overfitting by deterring them from reliance on particular features. A new approach reorganizes the process to run efficiently on the chips that typically run neural network calculations.

We’d all love to be able to find similar examples of our favorite cat videos. But few of us want to label thousands of similar videos of even the cutest kitties. New research makes headway in video classification when training examples are scarce.

Need a wardrobe upgrade? You could ask the fashion mavens at Netflix’s Queer Eye — or you could use a new neural network. Researchers at Amazon propose Category-based Subspace Attention Network (CSA-Net) to predict and retrieve compatible garments and accessories that complement one another.

A cat rotated by any number of degrees is still a cat. It takes a lot of rotated training images to teach convolutional filters this simple fact. A new filter design has this common-sense knowledge built-in.

The latest update of the acclaimed real-time object detector You Only Look Once is more accurate than ever. Researchers at Taiwan’s Institute of Information Science Academia Sinica offer YOLOv4 — the first version not to include the architecture’s original creators.

Your body disturbs Wi-Fi signals as you move through them. New research takes advantage of the effect to recognize the presence of people. Yang Liu and colleagues at Syracuse University detected people in a room with a Wi-Fi router by analyzing the signal.

Given real-world constraints on memory and processing time, images are often downsampled before they’re fed into a neural network. But the process removes fine details, and that degrades accuracy. A new technique squeezes images with less compromise.