Apr 14, 2021

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.

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.

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.

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.

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.

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.

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...