Computer Science

A simple algorithm that revolutionizes how neural networks approach language is now taking on image classification as well. It may not stop there.

For the first time, experiments demonstrate the possibility of sharing secrets with perfect privacy — even when the devices used to share them cannot be trusted.

Algorithms that use the brain’s communication signal can now work on analog neuromorphic chips, which closely mimic our energy-efficient brains.

Two recent collaborations between mathematicians and DeepMind demonstrate the potential of machine learning to help researchers generate new mathematical conjectures.

Two researchers show that for neural networks to be able to remember better, they need far more parameters than previously thought.

Two teams have shown how quantum approaches can solve problems faster than classical computers, bringing physics and computer science closer together.

By using hypernetworks, researchers can now preemptively fine-tune artificial neural networks, saving some of the time and expense of training.

For years, intermediate measurements made it hard to quantify the complexity of quantum algorithms. New work establishes that those measurements aren’t necessary after all.

A new result shows that quantum information can theoretically be protected from errors just as well as classical information can.