Apr 14, 2021

6 Posts

Robots Supervise Robots, Bad Labels Plague Datasets, Large Language Models Learn Chinese, Transformers Assimilate GANs
Apr 14, 2021

Robots Supervise Robots, Bad Labels Plague Datasets, Large Language Models Learn Chinese, Transformers Assimilate GANs

Machine learning development is highly iterative. Rather than designing a grand system, spending months to build it, and then launching it and hoping for the best, it’s usually better to build a quick-and-dirty system, get feedback, and use that feedback to improve the system.
11 min read
System designed to isolate changes in the pose of a two-dimensional figure
Apr 14, 2021

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
CogView home website
Apr 14, 2021

Large Language Models for Chinese

Researchers unveiled competition for the reigning large language model GPT-3. Four models collectively called Wu Dao were described by Beijing Academy of Artificial Intelligence, a research collective funded by the Chinese government, according to Synced Review.
2 min read
Model identifying erroneous labels in popular datasets
Apr 14, 2021

Labeling Errors Everywhere

Key machine learning datasets are riddled with mistakes. Several benchmark datasets are shot through with incorrect labels. On average, 3.4 percent of examples in 10 commonly used datasets are mislabeled and the detrimental impact of such errors rises with model size.
2 min read
Operators working with factory machinery
Apr 14, 2021

Who Watches the Welders?

A robot inspector is looking over the shoulders of robot welders. Farm equipment maker John Deere described a computer vision system that spots defective joints, helping to ensure that its heavy machinery leaves the production line ready to roll.
1 min read
A generative adversarial network (GAN)
Apr 14, 2021

Image Generation Transformed

A recent generative adversarial network (GAN) produced more coherent images using modified transformers that replaced fully connected layers with convolutional layers. A new GAN achieved a similar end using transformers in their original form.
2 min read

Subscribe to The Batch

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