We investigate the potential of graph neural networks (GNNs) for transfer learning and improved molecular property prediction in the context of funnels or screening cascades characteristic of drug ...

Learning speed depends on both task structure and neural dynamics prior to learning, yet a theory connecting them has been missing. Inspired by the fluctuation-response relation, we derive two ...

While artificial intelligence (AI) has made remarkable achievements in domains like image recognition and natural language processing, it encounters fundamental challenges when trying to deal with ...

Engineers have uncovered an unexpected pattern in how neural networks -- the systems leading today's AI revolution -- learn, suggesting an answer to one of the most important unanswered questions in ...

AI thrives on data but feeding it the right data is harder than it seems. As enterprises scale their AI initiatives, they face the challenge of managing diverse data pipelines, ensuring proximity to ...

A team of astronomers led by Michael Janssen (Radboud University, The Netherlands) has trained a neural network with millions of synthetic black hole data sets. Based on the network and data from the ...

Giving AI a human-like memory limitation may actually help it learn language better. In their new proof-of-principle study, ...

For the past decade, AI researcher Chris Olah has been obsessed with artificial neural networks. One question in particular engaged him, and has been the center of his work, first at Google Brain, ...

Researchers build fleeting memory transformers with human-like memory decay, proving memory limits help AI learn grammar ...

AI thrives on data but feeding it the right data is harder than it seems. As enterprises scale their AI initiatives, they face the challenge of managing diverse data pipelines, ensuring proximity to ...

In the cerebral cortex, numerous neurons exchange information through junctions known as synapses. The strength of each synaptic connection changes depending on the activity levels of the neurons ...

“Neural networks are currently the most powerful tools in artificial intelligence,” said Sebastian Wetzel, a researcher at the Perimeter Institute for Theoretical Physics. “When we scale them up to ...