Neural ModelS#
NeMoS (Neural ModelS) is a statistical modeling framework optimized for systems neuroscience and powered by JAX. It streamlines the process of defining and selecting models, through a collection of easy-to-use methods for feature design.
The core of NeMoS includes GPU-accelerated, well-tested implementations of standard statistical models for systems neuroscience.
We provide:
A
GLMfor single neurons and aPopulationGLM, with a choice of observation models (Poisson,Negative Binomial,Gamma,Gaussian,Bernoulli) and aClassifierGLMfor categorical responses.A composable basis module for constructing and transforming model features.
Multiple regularization schemes:
Ridge,Lasso,GroupLasso, andElasticNet.
Run the following pip command in your virtual environment.
pip install nemos
New to NeMoS? Get the ball rolling with our quickstart.
Refresh your theoretical knowledge before diving into data analysis with our notes.
Already familiar with the concepts? Learn how you to process and analyze your data with NeMoS.
Explore fully worked examples to learn how to analyze neural recordings from scratch.
Access a detailed description of each module and function, including parameters and functionality.
Learning Resources: Neuromatch Academy’s Lessons | Cosyne 2018 Tutorial
Useful Links: Getting Help | Issue Tracker | Contributing Guidelines
License#
Open source, licensed under MIT.
Cite Us#
If you use NeMoS in academic work, please cite the software. See the Citation Guide and Bibliography for more details.
Support#
This package is supported by:
The Center for Computational Neuroscience, in the Flatiron Institute of the Simons Foundation.
The NIH BRAIN Initiative (1RF1MH133778).
