Strategies for modelling sub-cortical processes with RNNs
Tom Close (Twitter: @tomgclose, Mattermost: @tclose, Mastodon: @tclose@fediscience.org)
No response
Brainhack Australasia
This project is currently at the thought-bubble stage, but I am interested in different ways recurrent neural networks (RNNs) can be used to model interactions between sub-cortical structures such as the basal-ganglia, thalamus, red nucleus and cerebellum. Inspired by recent work proposing using cutting-edge RNNs to model interactions between sub-cortical structures I would like to explore how RNNs could be used to model other aspects of sub-cortical functions.
While there have been a number of analogies made between cortical regions and non-recurrent ANNs (e.g. convolutional neural networks and visual cortex), RNNs are almost certainly required to recapitulate the state changes and motor output driven by sub-cortical regions.
As this this project is just at conception, please feel free to find me at the Australian BrainHack to sit down and spit-ball some ideas.
https://github.com/tclose/bhg-subcortical-rnn
issue one: Read/bring some interesting papers to discuss
issue two: Bring knowledge of a particular sub-cortical pathway or cool new RNN architecture
https://mattermost.brainhack.org/brainhack/channels/bhg-subcortical-rnn
Sorry, don’t have this yet
Hopefully something about RNNs and sub-cortical anatomy/function
N/A
more
Contributors to the code repository will be listed in the AUTHORS file (when it is created) and ideally a paper could come out of this project eventually.
Leave this text if you don’t have an image yet.
other
0_concept_no_content
deep_learning, machine_learning, neural_networks, systems_neuroscience
other
Python
not_applicable
1_commit_push
No response
Hi @brainhackorg/project-monitors my project is ready!