Courtney J. Spoerer

TL;DR: It is established that recurrent models are required to understand information processing in the human ventral stream using time-resolved brain imaging and deep learning.

TL;DR: It is found that recurrent neural networks outperform feedforward control models at recognizing objects, both in the absence of occlusion and in all occlusions conditions, and suggests that the ubiquitous recurrent connections in biological brains are essential for task performance.

TL;DR: Individual differences among DNN instances that arise from varying only the random initialization of the network weights are investigated, demonstrating that this minimal change in initial conditions prior to training leads to substantial differences in intermediate and higher-level network representations, despite achieving indistinguishable network-level classification performance.

TL;DR: The results suggest that recurrent connectivity, a hallmark of biological visual systems, may be essential for understanding the accuracy, flexibility, and dynamics of human visual recognition.

TL;DR: This work investigates individual differences among DNN instances that arise from varying only the random initialization of the network weights, and finds the origins of the effects in an under-constrained alignment of category exemplars, rather than misaligned category centroids.