AI could one day help neuroscientists predict activity in the human brain, just like language models can predict the next word in a sentence.

After more than a decade of research into the neural connections in the brains of various organisms, Google Research, Harvard University and HHMI Janelia have created the Zebrafish Activity Prediction Benchmark (ZAPBench), a dataset and benchmark that can help researchers more accurately model brain activity in larval zebrafish.

We developed ZAPBench from our 4D recording of the larval zebrafish brain, which captured the activity of 70,000 neurons as they responded to different virtual reality stimuli like changing light and water currents. By predicting brain activity in smaller organisms like zebrafish, we’ve taken another step toward understanding more complex brains like our own, with the ultimate goal of demystifying fundamental human behavior and the neurological issues that may underlie human brain disease.

Learn more about how Google Research is advancing neuroscience.