Jess Thompson<p>My latest work “Zero-shot counting with a dual-stream neural network model” is now published in Neuron. We present evidence for an enactive theory of the role of posterior parietal cortex in visual scene understanding and structure learning. Like the primate brain, our model apprehends a visual scene via a sequence of foveated glimpses. Both glimpse contents and glimpse locations are fed into our model, enabling the model to learn abstractions that are grounded in action (here, eye movements) rather than merely in the sensory domain. We show that this architecture enables zero-shot generalization of a previously learned structure (numerosity) to new objects in new contexts in a setting where a vanilla CNN fails to generalize. Our model also replicates several signatures of (the development of) human counting behaviour and learns representations that mimic neural codes for space and number in the primate brain. <br><a href="https://neuromatch.social/tags/neuralnetworks" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>neuralnetworks</span></a> <a href="https://neuromatch.social/tags/compneuro" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>compneuro</span></a> <a href="https://neuromatch.social/tags/neuroscience" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>neuroscience</span></a> <a href="https://neuromatch.social/tags/4ECognition" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>4ECognition</span></a> <a href="https://neuromatch.social/tags/attention" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>attention</span></a> <br><a href="https://www.sciencedirect.com/science/article/pii/S0896627324007293" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">sciencedirect.com/science/arti</span><span class="invisible">cle/pii/S0896627324007293</span></a></p>