neural networks

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

If only scientists understood exactly how electrons act in molecules, they’d be able to predict the behavior of everything from experimental drugs to high-temperature superconductors. Following decades of physics-based insights, artificial intelligence systems are taking the next leap.

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

In computer simulations of possible universes, researchers have discovered that a neural network can infer the amount of matter in a whole universe by studying just one of its galaxies.

It’s simple enough for AI to seem to comprehend data, but devising a true test of a machine’s knowledge has proved difficult.

Tiny amounts of artificial noise can fool neural networks, but not humans. Some researchers are looking to neuroscience for a fix.

Results from neural networks support the idea that brains are “prediction machines” — and that they work that way to conserve energy.

The computational biologist Anne Carpenter creates software that brings the power of machine learning to researchers seeking answers in mountains of cell images.

A new model of learning centers on bursts of neural activity that act as teaching signals — approximating backpropagation, the algorithm behind learning in AI.