Graph showing Expire-span which enables attention to ignore tokens that aren’t useful to the task at hand
Machine Learning Research

Sharper Attention

Self-attention enables transformer networks to track relationships between distant tokens — such as text characters — in long sequences, but the computational resources required grow quadratically with input size.
2 min read
Image recognition examples
Machine Learning Research

Smaller Models, Bigger Biases

Compression methods like parameter pruning and quantization can shrink neural networks for use in devices like smartphones with little impact on accuracy — but they also exacerbate a network’s bias.
2 min read
Graphs, images and data related to the activation function known as ReLU
Machine Learning Research

Upgrade for ReLU

The activation function known as ReLU builds complex nonlinear functions across layers of a neural network, making functions that outline flat faces and sharp edges. But how much of the world breaks down into perfect polyhedra?
2 min read
Simpler multilayer neural network
Machine Learning Research

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
Frozen Pretrained Transformer (FPT) explained
Machine Learning Research

Transformers: Smarter Than You Think

The transformer architecture has shown an uncanny ability to model not only language but also images and proteins. New research found that it can apply what it learns from the first domain to the others.
2 min read
Series of images showing how single trained network generates 3D reconstructions of multiple scenes
Machine Learning Research

One Network, Many Scenes

To reconstruct the 3D world behind a set of 2D images, machine learning systems usually require a dedicated neural network for each scene. New research enables a single trained network to generate 3D reconstructions of multiple scenes.
2 min read
Image showing how object detectors work
Machine Learning Research

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
A four-legged robot walking over difficult and changing terrain
Machine Learning Research

Walking the Dog

A reinforcement learning system enabled a four-legged robot to amble over unfamiliar, rapidly changing terrain.
1 min read
Automated player learning by watching recorded gameplay
Machine Learning Research

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
Few-shot Learning with a Universal Template (FLUTE)
Machine Learning Research

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
Machine Learning Research

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
Two images showing the process of turning handwriting into text
Machine Learning Research

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
Neural networks generating novel views of a 3D scene based on existing pictures
Machine Learning Research

3D Scene Synthesis for the Real World

Researchers have used neural networks to generate novel views of a 3D scene based on existing pictures plus the positions and angles of the cameras that took them. In practice, though, you may not know the precise camera
2 min read
Architecture of vision-language tasks
Machine Learning Research

One Model for Vision-Language

Researchers have proposed task-agnostic architectures for image classification tasks and language tasks. New work proposes a single architecture for vision-language tasks.
2 min read
Protein structures
Machine Learning Research

What AI Knows About Proteins

Transformer models trained on sequences of amino acids that form proteins have had success classifying and generating viable sequences. New research shows that they also capture information about protein structure.
2 min read

Subscribe to The Batch

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