Robots trained via reinforcement learning usually study videos of robots performing the task at hand. A new approach used videos of humans to pre-train robotic arms.

Vision models can be improved by training them on several altered versions of the same image and also by encouraging their weights to be close to zero. Recent research showed that both can have adverse effects that may be difficult to detect.

Researchers have shown that it’s possible to train a computer vision model effectively on around 66 percent of the pixels in each training image. New work used 25 percent, saving computation and boosting performance to boot.

Transformers can learn a lot from sequential data like words in a book, but they’ve shown limited ability to learn from data in the form of a graph. A new transformer variant gives graphs due attention.

Adding layers to a neural network puts the “deep” in deep learning, but it also increases the chance that the network will get stuck during training. A new approach effectively trains transformers with an order of magnitude more layers than previous methods.

Engineers who design aircraft, aqueducts, and other objects that interact with air and water use numerical simulations to test potential shapes, but they rely on trial and error to improve their designs. A neural simulator can optimize the shape itself.

The computational systems known as cellular automata reproduce patterns of pixels by iteratively applying simple rules based loosely on the behavior of biological cells. New work extends their utility from reproducing images to generating new ones.

An object detector trained exclusively on urban images might mistake a moose for a pedestrian and express high confidence in its poor judgment. New work enables object detectors, and potentially other neural networks, to lower their confidence when they encounter unfamiliar inputs.

Linear regression may be the key statistical method in machine learning, but it didn’t get to be that way without a fight. Two eminent mathematicians claimed credit for it, and 200 years later the matter remains unresolved.

Vision Transformer and models like it use a lot of computation and memory when processing images. New work modifies these architectures to run more efficiently while adopting helpful properties from convolutions.

If you want to both synthesize data and find the probability of any given example — say, generate images of manufacturing defects to train a defect detector and identify the highest-probability defects — you may use the architecture known as a normalizing flow.

Vision Transformer (ViT) outperformed convolutional neural networks in image classification, but it required more training data. New work enabled ViT and its variants to outperform other architectures with less training data.

The emerging generation of trillion-parameter language models take significant computation to train. Activating only a portion of the network at a time can cut the requirement dramatically and still achieve exceptional results.

OpenAI’s DALL·E got an upgrade that takes in text descriptions and produces images in styles from hand-drawn to photorealistic. The new version is a rewrite from the ground up. It uses the earlier CLIP zero-shot image classifier to represent text descriptions.

A new approach aims to cure text generators of their tendency to produce nonsense. AI21 Labs launched Jurassic-X, a natural language processing system that combines neural networks and rule-based programs.