Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
Joel Dapello, Kohitij Kar, Martin Schrimpf, Robert B. Geary, Michael Ferguson, David Cox, James J. DiCarlo
This study improves AI models by aligning their representations with macaque brain data, enhancing behavioral alignment and adversarial robustness.
bioRxiv · Jul 1, 2022 · PreprintNeuroscience