Study: AI models fail to reproduce human judgements about rule violations
Models trained using common data-collection techniques judge rule violations more harshly than humans would, researchers report.
Models trained using common data-collection techniques judge rule violations more harshly than humans would, researchers report.
A new computer vision system turns any shiny object into a camera of sorts, enabling an observer to see around corners or beyond obstructions.
Researchers identify a property that helps computer vision models learn to represent the visual world in a more stable, predictable way.
The system they developed eliminates a source of bias in simulations, leading to improved algorithms that can boost the performance of applications.
These tunable proteins could be used to create new materials with specific mechanical properties, like toughness or flexibility.
With the right building blocks, machine-learning models can more accurately perform tasks like fraud detection or spam filtering.
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.
Researchers used machine learning to build faster and more efficient hash functions, which are a key component of databases.
The method enables a model to determine its confidence in a prediction, while using no additional data and far fewer computing resources than other methods.
A new study shows how large language models like GPT-3 can learn a new task from just a few examples, without the need for any new training data.