Engineering recurrent neural networks from task-relevant manifolds and dynamics.
Many cognitive processes involve transformations of distributed representations in neural populations, creating a need for population-level models. Recurrent neural network models fulfill this need, but there are many open questions about how their connectivity gives rise to dynamics that solve a ta...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-08-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1008128 |
| _version_ | 1818901928573140992 |
|---|---|
| author | Eli Pollock Mehrdad Jazayeri |
| author_facet | Eli Pollock Mehrdad Jazayeri |
| author_sort | Eli Pollock |
| collection | DOAJ |
| description | Many cognitive processes involve transformations of distributed representations in neural populations, creating a need for population-level models. Recurrent neural network models fulfill this need, but there are many open questions about how their connectivity gives rise to dynamics that solve a task. Here, we present a method for finding the connectivity of networks for which the dynamics are specified to solve a task in an interpretable way. We apply our method to a working memory task by synthesizing a network that implements a drift-diffusion process over a ring-shaped manifold. We also use our method to demonstrate how inputs can be used to control network dynamics for cognitive flexibility and explore the relationship between representation geometry and network capacity. Our work fits within the broader context of understanding neural computations as dynamics over relatively low-dimensional manifolds formed by correlated patterns of neurons. |
| first_indexed | 2024-12-19T20:27:33Z |
| format | Article |
| id | doaj.art-4e412cb1bd9244bca48f3c8723d5239c |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-12-19T20:27:33Z |
| publishDate | 2020-08-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-4e412cb1bd9244bca48f3c8723d5239c2022-12-21T20:06:48ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582020-08-01168e100812810.1371/journal.pcbi.1008128Engineering recurrent neural networks from task-relevant manifolds and dynamics.Eli PollockMehrdad JazayeriMany cognitive processes involve transformations of distributed representations in neural populations, creating a need for population-level models. Recurrent neural network models fulfill this need, but there are many open questions about how their connectivity gives rise to dynamics that solve a task. Here, we present a method for finding the connectivity of networks for which the dynamics are specified to solve a task in an interpretable way. We apply our method to a working memory task by synthesizing a network that implements a drift-diffusion process over a ring-shaped manifold. We also use our method to demonstrate how inputs can be used to control network dynamics for cognitive flexibility and explore the relationship between representation geometry and network capacity. Our work fits within the broader context of understanding neural computations as dynamics over relatively low-dimensional manifolds formed by correlated patterns of neurons.https://doi.org/10.1371/journal.pcbi.1008128 |
| spellingShingle | Eli Pollock Mehrdad Jazayeri Engineering recurrent neural networks from task-relevant manifolds and dynamics. PLoS Computational Biology |
| title | Engineering recurrent neural networks from task-relevant manifolds and dynamics. |
| title_full | Engineering recurrent neural networks from task-relevant manifolds and dynamics. |
| title_fullStr | Engineering recurrent neural networks from task-relevant manifolds and dynamics. |
| title_full_unstemmed | Engineering recurrent neural networks from task-relevant manifolds and dynamics. |
| title_short | Engineering recurrent neural networks from task-relevant manifolds and dynamics. |
| title_sort | engineering recurrent neural networks from task relevant manifolds and dynamics |
| url | https://doi.org/10.1371/journal.pcbi.1008128 |
| work_keys_str_mv | AT elipollock engineeringrecurrentneuralnetworksfromtaskrelevantmanifoldsanddynamics AT mehrdadjazayeri engineeringrecurrentneuralnetworksfromtaskrelevantmanifoldsanddynamics |