Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Strategies for modelling sub-cortical processes with RNNs #110

Open
2 tasks
tclose opened this issue Nov 29, 2022 · 0 comments
Open
2 tasks

Strategies for modelling sub-cortical processes with RNNs #110

tclose opened this issue Nov 29, 2022 · 0 comments

Comments

@tclose
Copy link
Member

tclose commented Nov 29, 2022

Title

Strategies for modelling sub-cortical processes with RNNs

Leaders

Tom Close (Twitter: @tomgclose, Mattermost: @tclose, Mastodon: @[email protected])

Collaborators

No response

Brainhack Global 2022 Event

Brainhack Australasia

Project Description

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.

Link to project repository/sources

https://github.com/tclose/bhg-subcortical-rnn

Goals for Brainhack Global

  • Identify hypothesised sub-cortical functions that would be good candidates for modelling
  • Identify the best tools to develop such models (e.g. PyTorch)
  • Come up with a collection of generic Python scripts/modules that can be used as a starting point for such projects
  • Publish some strategies and learnings on the process

Good first issues

  1. issue one: Read/bring some interesting papers to discuss

  2. issue two: Bring knowledge of a particular sub-cortical pathway or cool new RNN architecture

Communication channels

https://mattermost.brainhack.org/brainhack/channels/bhg-subcortical-rnn

Skills

  • Python: intermediate
  • ANNs concepts: intermediate
  • Brain anatomy: basic

Onboarding documentation

Sorry, don't have this yet

What will participants learn?

Hopefully something about RNNs and sub-cortical anatomy/function

Data to use

N/A

Number of collaborators

more

Credit to collaborators

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.

Image

Leave this text if you don't have an image yet.

Type

other

Development status

0_concept_no_content

Topic

deep_learning, machine_learning, neural_networks, systems_neuroscience

Tools

other

Programming language

Python

Modalities

not_applicable

Git skills

1_commit_push

Anything else?

No response

Things to do after the project is submitted and ready to review.

  • Add a comment below the main post of your issue saying: Hi @brainhackorg/project-monitors my project is ready!
  • Twitter-sized summary of your project pitch.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment