Technical Program

Paper Detail

Paper: PS-1A.17
Session: Poster Session 1A
Location: H Lichthof
Session Time: Saturday, September 14, 16:30 - 19:30
Presentation Time:Saturday, September 14, 16:30 - 19:30
Presentation: Poster
Publication: 2019 Conference on Cognitive Computational Neuroscience, 13-16 September 2019, Berlin, Germany
Paper Title: Subtractive gating improves generalization in working memory tasks
Manuscript:  Click here to view manuscript
License: Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
Authors: Milton Llera Montero, Gaurav Malhotra, Jeff Bowers, Rui Ponte Costa, University of Bristol, United Kingdom
Abstract: It is largely unclear how the brain learns to generalize to new situations. Although deep learning models offer great promise as potential models of the brain, they break down when tested on novel conditions not present in their training datasets. One of the most successful models in machine learning are gated-recurrent neural networks. Because of its working memory properties here we refer to these networks as working memory networks (WMN). We compare WMNs with a biologically motivated variant of these networks. In contrast to the multiplicative gating used by WMNs, this new variant operates via subtracting gating (subWMN). We tested these two models in a range of working memory tasks: orientation recall with distractors, orientation recall with addition distractors and memory addition, and a more challenging task: sequence recognition based on the machine learning handwritten digits dataset. We evaluated the generalization properties of these two networks for working memory tasks by measuring how well they copped with three working memory loads: memory maintenance over time, making memories distractor-resistant and memory updating. Across these tests subWMNs perform better and more robustly than WMNs. Overall, our work suggests that the brain may rely on subtractive gating for improved generalization in working memory tasks.