The information bottleneck (IB) principle is a powerful information‐theoretic framework that seeks to compress data representations while preserving the information most pertinent to a given task.

Deep neural networks (DNNs), the machine learning algorithms underpinning the functioning of large language models (LLMs) and other artificial intelligence (AI) models, learn to make accurate ...

In recent years, as the field of deep learning has matured, a small but growing group of researchers and technologists has begun to question the prevailing assumptions behind neural networks. Among ...

The simplified approach makes it easier to see how neural networks produce the outputs they do. A tweak to the way artificial neurons work in neural networks could make AIs easier to decipher.

We study deep neural networks and their use in semiparametric inference. We establish novel rates of convergence for deep feedforward neural nets. Our new rates are sufficiently fast (in some cases ...

Neural networks are one typical structure on which artificial intelligence can be based. The term neural describes their learning ability, which to some extent mimics the functioning of neurons in our ...

Researchers from the University of Tokyo in collaboration with Aisin Corporation have demonstrated that universal scaling laws, which describe how the properties of a system change with size and scale ...

Previously met with skepticism, AI won scientists a Nobel Prize for Chemistry in 2024 after they used it to solve the protein folding and design problem, and it has now been adopted by biologists ...