Drones navigate unseen environments with liquid neural networks
MIT researchers exhibit a new advancement in autonomous drone navigation, using brain-inspired liquid neural networks that excel in out-of-distribution scenarios.
Data
A method for designing neural networks optimally suited for certain tasks
With the right building blocks, machine-learning models can more accurately perform tasks like fraud detection or spam filtering.
Learning to grow machine-learning models
New LiGO technique accelerates training of large machine-learning models, reducing the monetary and environmental cost of developing AI applications.
New method accelerates data retrieval in huge databases
Researchers used machine learning to build faster and more efficient hash functions, which are a key component of databases.
Large language models are biased. Can logic help save them?
MIT researchers trained logic-aware language models to reduce harmful stereotypes like gender and racial biases.
Efficient technique improves machine-learning models’ reliability
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.
Helping companies deploy AI models more responsibly
MIT spinout Verta offers tools to help companies introduce, monitor, and manage machine-learning models safely and at scale.
3 Questions: Leo Anthony Celi on ChatGPT and medicine
The chatbot’s success on the medical licensing exam shows that the test — and medical education — are flawed, Celi says.