A growing body of literature shows that some steps in AI’s forward march may actually move sideways. A new study questions advances in metric learning.

Conversational agents have a tough job following the zigs and zags of human conversation. They’re getting better at it — thanks to yesterday’s technology. Amazon recently improved the Alexa chatbot’s ability to identify the current topic of conversation.

The words “big” and “large” have similar meanings, but they aren’t always interchangeable: You wouldn’t refer to an older, male sibling as your “large brother” (unless you meant to be cheeky). Choosing among words with similar meanings is critical in language tasks like translation.

AI learns human biases: In word vector space, “man is to computer programmer as woman is to homemaker,” as one paper put it. New research helps language models unlearn such prejudices.

Natural language processing lately has come to resemble an arms race, as the big AI companies build models that encompass ever larger numbers of parameters. Microsoft recently held the record — but not for long.

Language models can’t correct your misspellings or suggest the next word in a text without knowing what language you’re using. For instance, if you type “tac-,” are you aiming for “taco,” a hand-held meal in Spanish, or “taca,” a crown in Turkish?

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.

In any training dataset, some classes may have relatively few examples. A new technique can improve a trained model’s performance on such underrepresented classes. Researchers introduced a method that synthesizes extracted features of underrepresented classes.

Neuroscientists once thought they could train rats to navigate mazes by color. Rats don’t perceive colors at all. Instead, they rely on the distinct odors of different colors of paint. New work finds that neural networks are prone to this sort of misalignment between training goals and learning.

The latest update of the acclaimed real-time object detector You Only Look Once is more accurate than ever. Researchers at Taiwan’s Institute of Information Science Academia Sinica offer YOLOv4 — the first version not to include the architecture’s original creators.

Facebook recently rolled out its entry in the World’s Biggest Chatbot sweepstakes. In keeping with the company’s social-networking dominance, the bot is designed to excel at chitchat on any subject.

Progress in language models is spawning a new breed of chatbots and, unlike their narrow-domain forebears, they have the gift of gab. Recent research tests the limits of conversational AI.

Few-shot learning seeks to build models that adapt to novel tasks based on small numbers of training examples. This sort of learning typically involves complicated techniques, but researchers achieved state-of-the-art results using a simpler approach.

Like nurses who can’t decipher a doctor’s handwriting, machine learning models can’t decipher medical scans — without labels. Conveniently, natural language models can read medical records to extract labels for X-ray images.

Human teachers can teach more effectively by adjusting their methods in response to student feedback. It turns out that teacher networks can do the same.