Teaching Machines to Listen to All Their Sensors at Once

The new method uses deep neural networks to combine data from multiple sources more effectively. Tests show it outperforms existing approaches on standard benchmarks, with strong potential for use in automation, intelligent control, and data-driven engineering.

Somewhere inside a large manufacturing plant, a turbofan bearing is beginning to fail. It will not announce this clearly. One vibration sensor picks up a faint irregularity in the x-axis; another registers a slight temperature drift; a third is recording torque anomalies that might mean nothing at all. Each sensor, considered alone, tells only a … Read more

Shrunken AI Models Reveal How the Brain’s Visual Neurons Actually Work

ML technique "prunes" the model, to make it more compact.

Somewhere in the visual cortex of a macaque monkey, a single neuron fires every time a small dot appears in the right location. Not a circle, not a line — a dot, specifically, at a specific size. For decades, neuroscientists could describe this selectivity without really explaining it. Now, for the first time, they can … Read more

One Night of Sleep Data Can Predict Your Disease Risk Years Ahead

AI image of woman in a sleep lab

The next time someone hooks you up to a sleep study, those sensors tracking your brain waves and heartbeat may not just be  looking for snoring problems. They could be capturing something far more revealing: a physiological signature that can forecast whether you’ll develop Parkinson’s disease, suffer a heart attack, or face dementia, sometimes years … Read more

He Taught AI to Say “I Don’t Know”

Light rays are propagating smoothly through a noisy, high-dimensional space in this artist’s impression. The new ray tracing algorithm improves on previous methods by better averaging information over trajectories, making it many orders of magnitude faster for quantifying uncertainties in large neural networks.

Artificial intelligence can diagnose disease, write essays, and generate art. But it often refuses to admit when it’s wrong. Now, a University of Arizona astronomer has found a way to change that. In a preprint posted to arXiv, Peter Behroozi introduces a new method for reducing hallucinations in large-scale AI models by making them aware … Read more