Modeling Attention and Binding in the Brain through Recurrent Gating

Join us for a talk by Konrad Kording, Penn Integrated Knowledge Professor at the University of Pennsylvania. This talk is part of the Kempner Seminar Series, a research-level seminar series on recent advances in the field.

Attention is a key component of the visual system, essential for perception, learning, and memory. Attention can also be seen as a solution to the binding problem: concurrent attention to all parts of an entity allows separating it from the rest. However, the rich models of attention in computational neuroscience are generally not scaled to real-world problems and there are thus many behavioral and neural phenomena that current models cannot explain. I will talk about recurrent models of attention that are inspired by modern neural networks for image segmentation.

They conceptualize recurrent connections as a multi-stage internal gating process where bottom-up connections transmit features, while top-down and lateral connections transmit attentional gating signals. Our model can recognize and segment simple stimuli such as digits as well as objects in natural images and is able to be prompted with object labels, attributes or locations. It replicates a range of behavioral findings, such as object binding, selective attention, inhibition of return, and visual search. It also replicates a variety of neural findings, including increased activity for attended objects, features, and locations, attention-invariant tuning, and relatively late onset attention. Most importantly, our proposed model unifies decades of cognitive and neurophysiological findings of visual attention into a single principled architecture. Our results highlight that the ability to selectively and dynamically focus on specific parts of stimulus streams can help artificial neural networks to better generalize and align with human brains.

Coming from Longwood? Sign up to take the shuttle.