Cortically motivated recurrence enables task extrapolation

Vijay Veerabadran, Yuan Tang, Ritik Raina, Virginia R. de Sa

Keywords: cognitive science, recurrent neural networks, task extrapolation, out of distribution generalization, visual routines, path integration

TL;DR: Biologically inspired recurrent network solves (easy and) hard instances of a task with (less and) more iterations.

Abstract: Feedforward deep neural networks have become the standard class of models in the field of computer vision. Yet, they possess a striking difference relative to their biological counterparts which predominantly perform “recurrent” computations. Why do biological neurons evolve to employ recurrence pervasively? In this paper, we show that a recurrent network is able to flexibly adapt its computational budget during inference and generalize within-task across difficulties. Simultaneously in this study, we contribute a recurrent module we call LocRNN that is designed based on a prior computational model of local recurrent intracortical connections in primates to support such dynamic task extrapolation. LocRNN learns highly accurate solutions to the challenging visual reasoning problems of Mazes and PathFinder that we use here. More importantly, it is able to flexibly use less or more recurrent iterations during inference to zero-shot generalize to less- and more difficult instantiations of each task without requiring extra training data, a potential functional advantage of recurrence that biological visual systems capitalize on. Feedforward networks on the other hand with their fixed computational graphs only partially exhibit this trend, potentially owing to image-level similarities across difficulties. We also posit an intriguing tradeoff between recurrent networks’ representational capacity and their stability in the recurrent state space. Our work encourages further study of the role of recurrence in deep learning models – especially from the context of out-of-distribution generalization & task extrapolation – and their properties of task performance and stability.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)