Supervised Learning

One challenge to making online education available worldwide is evaluating an immense volume of student work. Especially difficult is evaluating interactive computer programming assignments such as coding a game.

A new coding framework lets you pipe your own data into large language models. LlamaIndex streamlines the coding involved in enabling developers to summarize, reason over, and otherwise manipulate data from documents, databases, and apps using models like GPT-4.

Things are really starting to get going in the field of AI. After many years (decades?!) of focusing on algorithms, the AI community is finally ready to accept the central role of data and the high-capacity models that are capable of taking advantage of this data.

Models trained using supervised learning struggle to classify inputs that differ substantially from most of their training data. A new method helps them recognize such outliers.

Playing a team sport involves a fluid blend of individual and group skills. Researchers integrated both types of action into realistic humanoid agents that play football (known as soccer in the U.S.).

Neural networks are famously bad at interpreting input that falls outside the training set’s distribution, so it’s not surprising that some models are certain that cat pictures show symptoms of Covid-19. A new approach won’t mistakenly condemn your feline to a quarantine.

Robot vacuum cleaners are pretty good at navigating rooms, but they still get stuck in tight spaces. New work takes a step toward giving them the smarts they’ll need to escape the bathroom.

Machine learning promises to streamline handling of tomorrow’s bureaucratic drudgery — and, it turns out, that of 2,500 years ago. Computer vision is helping researchers at the University of Chicago translate a massive collection of ancient records inscribed on clay tablets.

Geoffrey Hinton, Yoshua Bengio, and Yann LeCun presented their latest thinking about deep learning’s limitations and how to overcome them.

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.