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.
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.
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.
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.
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.
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.
Simplified depiction of LSH Attention
UC Berkeley

Transformers Transformed

Transformer networks have revolutionized natural language processing, but they hog processor cycles and memory. New research demonstrates a more frugal variation.
Capture of an Instagram post related to drug dealing
UC Berkeley

Hunting Online Drug Dealers

Can machine learning help address the scourge of opioid addiction? A public health researcher developed a neural network that spots sellers of opioids on social media, Recode reported.
Dawn Song
UC Berkeley

Dawn Song: Taking Responsibility for Data

Datasets are critical to AI and machine learning, and they are becoming a key driver of the economy. Collection of sensitive data is increasing rapidly, covering almost every aspect of people’s lives.
David Patterson
UC Berkeley

David Patterson: Faster Training and Inference

Billions of dollars invested to create novel AI hardware will bear their early fruit in 2020. Google unleashed a financial avalanche with its tensor processing unit in 2017.
Examples of finished virtual pencil sketches (shoe and headshot)
UC Berkeley

Unfinished Artwork? No More

Generative networks can embroider sentences into stories and melodies into full-fledged arrangements. A new model does something similar with drawings.
Original vs Deepfake example
UC Berkeley

Facing Down Deepfakes

Deepfakes threaten to undermine law and order, perhaps democracy itself. A coalition of tech companies, nonprofits, and academics joined forces to counter potential adverse impacts.

Subscribe to The Batch

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