Joel Dapello

This study improves AI models by aligning their representations with macaque brain data, enhancing behavioral alignment and adversarial robustness.

This study shows that the primary visual cortex encodes head direction signals in freely behaving rats, supporting predictive coding theories.

A fixed-weight, biologically parameterised V1 front-end gives standard image classifiers adversarial and corruption robustness at no extra training cost; its simulated neuronal noise drives most of the adversarial gain.