Machine Learning Research

A reinforcement learning model maintains cooler temperatures in large data centers and other buildings.

While transformers have delivered state-of-the-art results in several domains of machine learning, few attempts have been made to probe their inner workings. Researchers offer a new approach.

Vision transformers have bested convolutional neural networks (CNNs) in a number of key vision tasks. Have CNNs hit their limit? New research suggests otherwise.

The ability of OpenAI’s CLIP to produce similar embeddings of a text phrase and a matching image opened up applications like classifying images according to labels that weren’t in the training set. A new model extends this capability to seven data types.

Text-to-video generation is so 2022! A new system takes in text and generates an animated 3D scene that can be viewed or rendered from any angle.

Vision transformers typically process images in patches of fixed size. Smaller patches yield higher accuracy but require more computation. A new training method lets AI engineers adjust the tradeoff.

Large language models increasingly reply to prompts with a believably human response. Can they also mimic human behavior?

A tweak to diffusion models, which are responsible for most of the recent excitement about AI-generated images, enables them to produce more realistic output.

Machine learning models have predicted weather a few days ahead of time. A new approach substantially extends the time horizon. Remi Lam and colleagues at Google developed GraphCast, a weather-forecasting system based on graph neural networks (GNNs).

Reinforcement learning agents have mastered games like Go that provide complete information about the state of the game to players. They’ve also excelled at Texas Hold ’Em poker, which provides incomplete information, as few cards are revealed.

During training, a neural network usually updates its weights according to an optimizer that’s tuned using hand-picked hyperparameters. New work eliminates the need for optimizer hyperparameters.

Training an agent that controls a robot arm to perform a task — say, opening a door — that involves a sequence of motions (reach, grasp, turn, pull, release) can take from tens of thousands to millions of examples...

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.

Fine-tuning a neural network typically involves retraining every layer on new data. But research shows that networks may perform better when fine-tuning modifies only a subset of layers.

A pretrained text-to-image generator enabled researchers to see — roughly — what other people looked at based on brain scans. Yu Takagi and Shinji Nishimoto developed a method that uses Stable Diffusion to reconstruct images viewed by test subjects...