Animation showing AlphaFold working
Convolutional Neural Networks (CNN)

Biomedical Treasure Chest

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.
2 min read
Simpler multilayer neural network
Convolutional Neural Networks (CNN)

Revenge of the Perceptrons

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.
2 min read
Image showing how object detectors work
Convolutional Neural Networks (CNN)

I Know It When I See It

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.
2 min read
Automated player learning by watching recorded gameplay
Convolutional Neural Networks (CNN)

Behavioral Cloning Shootout

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.
2 min read
Series of imagen showing how an insect-sorting robot works
Convolutional Neural Networks (CNN)

Bugbot

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.
2 min read
Few-shot Learning with a Universal Template (FLUTE)
Convolutional Neural Networks (CNN)

Pattern for Efficient Learning

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.
2 min read
AI generated videos and VideoGPT training pipeline
Convolutional Neural Networks (CNN)

Synthetic Videos on the Double

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.
2 min read
Computer vision is probing the history of ancient pottery
Convolutional Neural Networks (CNN)

Sorting Shattered Traditions

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.
1 min read
Two images showing the process of turning handwriting into text
Convolutional Neural Networks (CNN)

The Writing, Not the Doodles

Systems designed to turn handwriting into text typically work best on pages with a consistent layout, such as a single column unbroken by drawings, diagrams, or extraneous symbols. A new system removes that requirement.
2 min read
A new metod for compressing images and yielding better classification
Convolutional Neural Networks (CNN)

What Machines Want to See

Researchers typically downsize images for vision networks to accommodate limited memory and accelerate processing. A new method not only compresses images but yields better classification.
1 min read
Surgical robots performing different actions
Convolutional Neural Networks (CNN)

Medical AI Gets a Grip

Surgical robots perform millions of delicate operations annually under human control. Now they’re getting ready to operate on their own.
2 min read
System designed to isolate changes in the pose of a two-dimensional figure
Convolutional Neural Networks (CNN)

Motion Mapper

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.
2 min read
Data related to SElf-supERvised (SEER), an image classifier pretrained on uncurated, unlabeled images
Convolutional Neural Networks (CNN)

Pretraining on Uncurated Data

It’s well established that pretraining a model on a large dataset improves performance on fine-tuned tasks. In sufficient quantity and paired with a big model, even data scraped from the internet at random can contribute to the performance boost.
2 min read
Sequence related to image processing
Convolutional Neural Networks (CNN)

Vision Models Get Some Attention

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.
2 min read

Subscribe to The Batch

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