Odelia Schwartz

This study examines the structure of trial-by-trial neural co-variance in dropout neural networks and finds it similar to biological neural variability, suggesting potential implications for network performance and modeling.

The paper uses deep neural networks to study surround suppression in visual processing, finding that networks exhibit similar contextual effects to biological systems, especially in complex stimuli.

The paper introduces a brain-inspired weighted normalization method for CNNs, showing improved performance on image classification tasks across multiple datasets.