Kandan Ramakrishnan

The paper identifies a dual-feature encoding strategy in visual cortical neurons where neurons respond to both enhancing and suppressing visual features, showing this strategy is conserved across species.

The paper uses multi-task deep neural networks to analyze visual pathway organization, finding that unrelated tasks lead to less feature sharing in higher layers.

This study examines how the depth of convolutional neural networks (CNNs) correlates with EEG responses during visual object recognition, showing that deeper CNNs improve predictions after 150 ms.