Spyking AI

[marco7877]

Title

Spyking AI

This project aims to build a Tensorflow wrapper to build and train spiking neuron arrays connected though hebbian conections. This tool is proposed to study neural mechanisms during cognitive events, i.e., language production/comprehension

Leaders

Marco Antonio Flores Coronado @MarcoFloresCoro

Collaborators

No response

Brainhack Global 2023 Event

Brainhack Donostia

Project Description

• What are you doing, for whom, and why?
• We are building a new tool to study neural association between cortical regions. This will prove to be useful for cognitive and neural researchers
• What makes your project special and exciting?
• this will be the first spiking neuron based library aimed for cognitive research. Several other spiking neuron libraries exist, however those follow linear architectures to resemble DNN
• How to get started?
• The library will be based on Pulvermüller, F. (2013). How neurons make meaning: Brain mechanisms for embodied and abstract-symbolic semantics. Trends in Cognitive Sciences, 17(9), 458–470. https://doi.org/10.1016/j.tics.2013.06.004
  and Constant, M., Pulvermüller, F., & Tomasello, R. (2023). Brain-constrained neural modeling explains fast mapping of words to meaning. Cerebral Cortex, bhad007. https://doi.org/10.1093/cercor/bhad007 .
• Where to find key resources?
  see above

Link to project repository/sources

.

Goals for Brainhack Global

1. To build a spiking neuron class
2. To build a hebbian learning class
3. To train a dummy model associating spiking patterns with one hot vectors
4. Write documentation

Good first issues

1. issue one:

2. issue two:

Communication channels

NaN

Skills

• Python: medium & advanced
• Markdown: beginner
• Cognitive neuroscience background

Onboarding documentation

No response

What will participants learn?

To build a Tensorflow wrapper and a introduction to AI

Data to use

No response

Number of collaborators

4

Credit to collaborators

Contributors will be part of the github repo. They will be co-authors of any further publication

Image

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

Type

coding_methods, pipeline_development

Development status

0_concept_no_content

Topic

deep_learning, machine_learning, neural_networks, systems_neuroscience

Tools

Jupyter

Programming language

Python

Modalities

not_applicable

Git skills

1_commit_push, 2_branches_PRs

Anything else?

l

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.

[marco7877]

@brainhackorg/project-monitors my project is ready!

[crnolan]

Hi @marco7877, if you have no good first issues, do you want to remove the default text from the field?

Also, the text in these fields will be published as-is, so for example the dot-points in the project description will come out exactly as they are written above, is that ok?