Animated chart shows how AI can help robots locate key spatial coordinates.
Convolutional Neural Network (CNN)

Finding Useful Points in Space: Keypoint3D Helps Robots Locate Spatial Coordinates

A new machine learning method aims to improve a machine’s ability to determine and locate points of interest.
An animation of a protein modeled by AlphaFold 2.
Convolutional Neural Network (CNN)

DeepMind Doubles Down on AlphaFold: DeepMind Launches Company to Commercialize AlphaFold 2

Isomorphic aims to build its business on AlphaFold 2, an ensemble of neural networks that finds the shapes of protein molecules.
Animation showing the use of AI to identify forgery in a famous painting
Convolutional Neural Network (CNN)

Seeing Through Forgeries: Researchers Use AI to Identify Da Vinci Forgery

Accusations of fraud hang over some of the world’s most highly valued artworks. Machine learning engineers are evaluating the authenticity of these famous pieces.
Animated video showing an image generator imitating brush strokes
Convolutional Neural Network (CNN)

Different Strokes for Robot Folks: Transformer-Based Image Generator Imitates Painters

A neural network can make a photo resemble a painting via neural style transfer, but it can also learn to reproduce an image by applying brush strokes. A new method taught a system this painterly skill without any training data.
The Sun through a space telescope with a calibrated and uncalibrated focus.
Convolutional Neural Network (CNN)

Solar System: AI Helps NASA Calibrate its Solar Telescopes

Astronomers may use deep learning to keep the sun in focus.What’s new: Researchers at the U.S. National Aeronautics and Space Administration (NASA), Catholic University of America, University of Oslo, and elsewhere developed a model that helps recalibrate a space telescope focused on the sun.
Sequence of famous arcade games' scenes
Convolutional Neural Network (CNN)

Solve RL With This One Weird Trick: How to get better performance from reinforcement learning.

The previous state-of-the-art model for playing vintage Atari games took advantage of a number of advances in reinforcement learning (RL). The new champion is a basic RL architecture plus a trick borrowed from image generation.
Animation showing AlphaFold working
Convolutional Neural Network (CNN)

Biomedical Treasure Chest: DeepMind open sources AlphaFold and protein databases.

DeepMind opened access to AlphaFold, a model that finds the shapes of proteins, and to its output so far — a potential cornucopia for biomedical research. The research lab, a division of Google’s parent company Alphabet, made AlphaFold freely available.
Simpler multilayer neural network
Convolutional Neural Network (CNN)

Revenge of the Perceptrons: Perceptrons do some AI tasks on par with complex AI.

Why use a complex model when a simple one will do? New work shows that the simplest multilayer neural network, with a small twist, can perform some tasks as well as today’s most sophisticated architectures.
Image showing how object detectors work
Convolutional Neural Network (CNN)

I Know It When I See It: Zero-shot detection for objects not in training data.

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.
Automated player learning by watching recorded gameplay
Convolutional Neural Network (CNN)

Behavioral Cloning Shootout: AI learns to play Counter Strike Global Offensive.

Neural networks have learned to play video games like Dota 2 via reinforcement learning by playing for the equivalent of thousands of years (compressed into far less time). In new work, an automated player learned not by playing for millennia but by watching a few days’ worth of recorded gameplay.
Series of imagen showing how an insect-sorting robot works
Convolutional Neural Network (CNN)

Bugbot: How AI can help with the insect biodiversity crisis.

An insect-sorting robot could help scientists grapple with the global biodiversity crisis. An automated insect classifier sucks in tiny arthropods, classifies them, and maps their most important identifying features.
Few-shot Learning with a Universal Template (FLUTE)
Convolutional Neural Network (CNN)

Pattern for Efficient Learning: A training method for few-shot learning in computer vision.

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.
AI generated videos and VideoGPT training pipeline
Convolutional Neural Network (CNN)

Synthetic Videos on the Double: VideoGPT is an efficient generative AI system for video.

Using a neural network to generate realistic videos takes a lot of computation. New work performs the task efficiently enough to run on a beefy personal computer.
Fire-spotting cameras alerting a fire engine
Convolutional Neural Network (CNN)

Where There’s Smoke, There’s AI: Computer vision system can see wildfire smoke.

An automated early warning system is alerting firefighters to emerging blazes.
Graphs and pictures showing how computer vision classifies pottery
Convolutional Neural Network (CNN)

Sorting Shattered Traditions: Archaeologists use machine learning to classify pottery.

Computer vision is probing the history of ancient pottery | What’s new: Researchers at Northern Arizona University developed a machine learning model that identifies different styles of Native American painting on ceramic fragments and sorts the shards by historical period.

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox