Probabilistic AI that knows how well it’s working
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
It’s more important than ever for artificial intelligence to estimate how accurately it is explaining data.
Researchers identify a property that helps computer vision models learn to represent the visual world in a more stable, predictable way.
With further development, the programmable system could be used in a range of applications including gene and cancer therapies.
MIT researchers uncover the structural properties and dynamics of deep classifiers, offering novel explanations for optimization, generalization, and approximation in deep networks.
The program leverages MIT’s research expertise and Takeda’s industrial know-how for research in artificial intelligence and medicine.
A new tool brings the benefits of AI programming to a much broader class of problems.