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

July 7, 20212 min read
Bugbot: How AI can help with the insect biodiversity crisis.
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.

July 7, 20212 min read
Bugbot: How AI can help with the insect biodiversity crisis.
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.

July 7, 20212 min read
Pattern for Efficient Learning: A training method for few-shot learning in computer vision.
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.

June 30, 20212 min read
Pattern for Efficient Learning: A training method for few-shot learning in computer vision.
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.

June 30, 20212 min read
Synthetic Videos on the Double: VideoGPT is an efficient generative AI system for video.
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.

June 23, 20212 min read
Synthetic Videos on the Double: VideoGPT is an efficient generative AI system for video.
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.

June 23, 20212 min read
Where There’s Smoke, There’s AI: Computer vision system can see wildfire smoke.
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.

June 23, 20211 min read
Where There’s Smoke, There’s AI: Computer vision system can see wildfire smoke.
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.

June 23, 20211 min read
Sorting Shattered Traditions: Archaeologists use machine learning to classify 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.

June 23, 20211 min read
Sorting Shattered Traditions: Archaeologists use machine learning to classify 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.

June 23, 20211 min read
The Writing, Not the Doodles: A handwriting detection AI model for messy paper.
Convolutional Neural Network (CNN)

The Writing, Not the Doodles: A handwriting detection AI model for messy paper.

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.

June 16, 20212 min read
The Writing, Not the Doodles: A handwriting detection AI model for messy paper.
Convolutional Neural Network (CNN)

The Writing, Not the Doodles: A handwriting detection AI model for messy paper.

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.

June 16, 20212 min read
What Machines Want to See: An image compressor for more accurate computer vision
Convolutional Neural Network (CNN)

What Machines Want to See: An image compressor for more accurate computer vision

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.

May 26, 20211 min read
What Machines Want to See: An image compressor for more accurate computer vision
Convolutional Neural Network (CNN)

What Machines Want to See: An image compressor for more accurate computer vision

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.

May 26, 20211 min read

Subscribe to The Batch

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