The secrets of history are locked in troves of handwritten documents. Now a machine learning platform is making them amenable to digital search. Transkribus is transcribing centuries-old records en masse and making them available to scholars worldwide.

A new study used AI to track the explosive growth of AI innovation. Researchers from the U.S. Patent and Trademark Office deployed natural language processing to track AI’s increasing presence in four decades of patent data.

Amazon’s digital assistant is using its eyes as well as its ears to figure out who’s talking. At its annual hardware showcase, Amazon introduced an Alexa skill that melds acoustic, linguistic, and visual cues to help the system keep track of individual speakers and topics of conversation.

When the chips are down, humans can track critical details without being distracted by irrelevancies. New research helps reinforcement learning models similarly focus on the most important details.

Machine learning researchers report better and better results, but some of that progress may be illusory. Some models that appear to set a new state of the art haven’t been compared properly to their predecessors, Science News reports based on several published surveys.

Generative adversarial networks don’t just produce pretty pictures. They can build world models, too. A GAN generated a fully functional replica of the classic video game Pac-Man.

The latest large, pretrained language models rely on trendy layers based on transformer networks. New research shows that these newfangled layers may not be necessary.

Large NLP models like BERT can answer questions about a document thanks to the transformer network, a sequence-processing architecture that retains information across much longer sequences than previous methods. But transformers have had little success in reinforcement learning — until now.

Weak supervision is the practice of assigning likely labels to unlabeled data using a variety of simple labeling functions. Then supervised methods can be used on top of the now-labeled data.

Humans understand the world by abstraction: If you grasp the concept of grabbing a stick, then you’ll also comprehend grabbing a ball. New work explores deep learning agents’ ability to do the same thing — an important aspect of their ability to generalize.