アイテム詳細

要旨

Artificial Intelligence (AI) has the potential to sig- nificantly advance scientific discovery by finding solutions beyond human capabilities. However, these super-human solutions are often unintuitive and require considerable effort to uncover under- lying principles, if possible at all. Here, we show how a code-generating language model trained on synthetic data can not only find solutions to specific problems but can create meta-solutions, which solve an entire class of problems in one shot and simultaneously offer insight into the underlying design principles. Specifically, for the design of new quantum physics experiments, our sequence-to-sequence transformer architec- ture generates interpretable Python code that de- scribes experimental blueprints for a whole class of quantum systems. We discover general and pre- viously unknown design rules for infinitely large classes of quantum states. The ability to automat- ically generate generalized patterns in readable computer code is a crucial step toward machines that help discover new scientific understanding – one of the central aims of physics.