Machine-learning algorithms can guide humans toward new experiments and theories
They are designing neural networks that suggest new hypotheses based on patterns the networks find in data instead of relying on human assumptions.
The researchers developed a neural network that ranked chemical combinations by how likely they were to result in a useful new material.
Before A.I. can uncover the true nature of reality, researchers must tackle the notoriously difficult question of how neural networks make their decisions.
Neural networks are built from interconnected nodes, modeled after the neurons of the brain, with a structure that changes as information flows through it.
Some scientists are trying to make the black box transparent by developing "Interpretability techniques," which attempt to offer a step-by-step explanation for how a network arrives at its answers.
The neural network cannot yet explain why the density of glands' structure contributes to cancer, but it still helped Madabhushi and his colleagues better understand how tumor growth progresses, leading to new directions for future research.
One neural network, called Correctional Offender Management Profiling for Alternative Sanctions, was even accused of being racist.
Neural networks could inspire people to think about old questions in new ways, he says.
While the networks cannot yet make hypotheses entirely by themselves, they can give hints and direct scientists toward a different view of a problem.
Renner is going so far as to try designing a neural network that can examine the true nature of the cosmos.