Giter VIP home page Giter VIP logo

Comments (5)

craree avatar craree commented on September 27, 2024

The version you installed by 'pip install braincog' is inconsistent with the online version on GitHub. You can clone braincog from github(see https://www.brain-cog.network/docs/tutorial/1_installation.html):
git clone https://github.com/braincog-X/Brain-Cog.git
cd Brain-Cog
pip install -e .
Or you can copy the code of HHNode and aEIF in braincog/base/node/node.py on github

from brain-cog.

lonnietc avatar lonnietc commented on September 27, 2024

Thanks for getting back to me on this.

What version of Python do you typically use?

Also, I actually followed the install tutorial

https://www.youtube.com/watch?v=XkHq-MbKo20&list=PLNXUFsTshMlYTW6oleY5YjVEfnoQSw0N7&index=2

with references to the Brain Cod Github repo information as well.

from brain-cog.

lonnietc avatar lonnietc commented on September 27, 2024

I did a clean re-install of Brain Cog and things seem to run now with just on "UserWarning"


D:\BrainCog\Brain-Cog\examples\Multiscale_Brain_Structure_Simulation\HumanBrain\human_brain.py:201: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).
  Iraster = torch.tensor(Iraster).transpose(0, 1)

Also, is there somewhere I can get the paper since I do not have access to this particular one from where I am at:

    @article{Liu2016,
    author={Liu, Xin and Zeng, Yi and Zhang, Tielin and Xu, Bo},
    title={Parallel Brain Simulator: A Multi-scale and Parallel Brain-Inspired Neural Network Modeling and Simulation Platform},
    journal={Cognitive Computation},
    year={2016},
    month={Oct},
    day={01},
    volume={8},
    number={5},
    pages={967--981},
    issn={1866-9964},
    doi={10.1007/s12559-016-9411-y},
    url={https://doi.org/10.1007/s12559-016-9411-y}

from brain-cog.

craree avatar craree commented on September 27, 2024

I think a python version over 3.7 is sufficient.

The methods in this article are not what our current code uses. I share the paper in the following link:
https://drive.google.com/file/d/1p-ewKNzUFaAgf3jKa0FcE-yWPHI7iWoT/view?usp=sharing

from brain-cog.

lonnietc avatar lonnietc commented on September 27, 2024

Thanks for the quick response and for the paper link that I will read with great interest.

I will give the Python 3.7 a try to see how it runs the examples to see how that goes.

Eventually, I would like to see about adding some new models to the Brain Cog Model_Zoo since I think that it could be helpful for the eventual modeling of a virtual full brain simulation towards AGI.

One step forward would be to work out a good spiking RNN approach for a Question & Answering system maybe building on something in the "Knowledge Representation and Reasoning" section.

Thanks again

from brain-cog.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.