Interpretability

By tapping into a decades-old mathematical principle, researchers are hoping that Kolmogorov-Arnold networks will facilitate scientific discovery.

To better understand how neural networks learn to simulate writing, researchers trained simpler versions on synthetic children’s stories.

Cynthia Rudin wants machine learning models, responsible for increasingly important decisions, to show their work.

Language processing programs are notoriously hard to interpret, but smaller versions can provide important insights into how they work.

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

To help them explain the shocking success of deep neural networks, researchers are turning to older but better-understood models of machine learning.

Neural networks can be as unpredictable as they are powerful. Now mathematicians are beginning to reveal how a neural network’s form will influence its function.

Neural networks are famously incomprehensible, so Been Kim is developing a “translator for humans.”

A new idea is helping to explain the puzzling success of today’s artificial-intelligence algorithms — and might also explain how human brains learn.