UC Berkeley

21 Posts

A living room made out of cups of coffee: the people, the seats, the chimney, the lamp, all gather around a cozy fire.
UC Berkeley

One Architecture to Do Them All: Transformer: The AI Architecture That Can Do It All

The transformer architecture extended its reach to a variety of new domains.What happened: Originally developed for natural language processing, transformers are becoming the Swiss Army Knife of deep learning.
2 min read
An illustration shows a cozy cabin where all the furniture is made out of coffee mugs.
UC Berkeley

Transformers Take Over: Transformers Applied to Vision, Language, Video, and More

In 2021, transformers were harnessed to discover drugs, recognize speech, and paint pictures — and much more.
2 min read
Detection of a digitally altered image of a frog holding a violin
UC Berkeley

Fighting Fakes

A supergroup of machine learning models flags manipulated photos. Jigsaw, a tech incubator owned by Alphabet, released a system that detects digitally altered images.
1 min read
Frozen Pretrained Transformer (FPT) explained
UC Berkeley

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
Animated video showing a system to interpret electrical impulses from the brain as words
UC Berkeley

Listening to the Brain

Neural networks translated a paralyzed man’s brainwaves into conversational phrases. Researchers trained a system to interpret electrical impulses from the brain of a man who had lost the ability to speak 15 years ago, and displayed them as words on a video screen.
1 min read
A four-legged robot walking over difficult and changing terrain
UC Berkeley

Walking the Dog

A reinforcement learning system enabled a four-legged robot to amble over unfamiliar, rapidly changing terrain.
1 min read
Surgical robots performing different actions
UC Berkeley

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
Animation showing a methaforical transition from AI to a green environment
UC Berkeley

Greener Machine Learning

A new study suggests tactics for machine learning engineers to cut their carbon emissions. Led by David Patterson, researchers at Google and UC Berkeley found that AI developers can shrink a model’s carbon footprint a thousand-fold by streamlining architecture...
1 min read
Sequence related to image processing
UC Berkeley

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
Examples of InstaHide scrambling images
UC Berkeley

A Privacy Threat Revealed

With access to a trained model, an attacker can use a reconstruction attack to approximate its training data. A method called InstaHide recently won acclaim for promising to make such examples unrecognizable to human eyes while retaining their utility for training.
2 min read
Data related to a technique that uses a neural network to compute the progress of a fluid dynamics simulation
UC Berkeley

Physics Simulations Streamlined

Computer simulations do a good job of modeling physical systems from traffic patterns to rocket engines, but they can take a long time to run. New work takes advantage of deep learning to speed them up.
2 min read
Data and examples related to IMLE-GAN
UC Berkeley

Making GANs More Inclusive

A typical GAN’s output doesn’t necessarily reflect the data distribution of its training set. Instead, GANs are prone to modeling the majority of the training distribution, sometimes ignoring rare attributes — say, faces that represent minority populations.
2 min read
Information related to Policy Adaptation during Deployment (Pad)
UC Berkeley

Same Job, Different Scenery

People who take driving lessons during daytime don’t need instruction in driving at night. They recognize that the difference doesn’t disturb their knowledge of how to drive. Similarly, a new reinforcement learning method manages superficial variations in the environment without re-training.
2 min read
Graphs and data related to Plan2Vec
UC Berkeley

Visual Strategies for RL

Reinforcement learning can beat humans at video games, but humans are better at coming up with strategies to master more complex tasks. New work enables neural networks to connect the dots.
2 min read
Examples of recognition of real and fake images
UC Berkeley

Fake Detector

AI’s ability to produce synthetic pictures that fool humans into believing they’re real has spurred a race to build neural networks that can tell the difference. Recent research achieved encouraging results.
2 min read

Subscribe to The Batch

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