Sep 21 – 23, 2021
Europe/Berlin timezone

The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning

Sep 22, 2021, 3:30 PM


Talk Neuro-Inspired AI Contributed Talks: Neuro-Inspired AI


Shahab Bakhtiari (McGill University, Mila)


The visual system of mammals is comprised of parallel, hierarchical specialized pathways. Different pathways are specialized in so far as they use representations that are more suitable for supporting specific downstream behaviours. In particular, the clearest example is the specialization of the ventral (“what”) and dorsal (“where”) pathways of the visual cortex. These two pathways support behaviours related to visual recognition and movement, respectively. To-date, deep neural networks have mostly been used as models of the ventral, recognition pathway. However, it is unknown whether both pathways can be modelled with a single deep ANN. Here, we ask whether a single model with a single loss function can capture the properties of both the ventral and the dorsal pathways. We explore this question using data from mice, who like other mammals, have specialized pathways that appear to support recognition and movement behaviours. We show that when we train a deep neural network architecture with two parallel pathways using a self-supervised predictive loss function, we can outperform other models in fitting mouse visual cortex. Moreover, we can model both the dorsal and ventral pathways. These results demonstrate that a self-supervised predictive learning approach applied to parallel pathway architectures can account for some of the functional specialization seen in mammalian visual systems.

Primary author

Shahab Bakhtiari (McGill University, Mila)


Patrick Mineault Timothy Lillicrap (DeepMind) Christopher Pack (McGill University) Blake Richards (McGill University, Mila)

Presentation materials

There are no materials yet.