Priesemann-Group/nninfo
A Python Package for the Analysis of Deep Neural Networks using Information Theory
This tool helps researchers analyze how deep neural networks process and represent information. By inputting network architectures and training data, it outputs detailed measures of information flow and complexity within the network layers. This allows neuroscientists, machine learning researchers, and cognitive scientists to understand the underlying mechanisms of deep learning models.
Use this if you are a researcher who needs to quantify and understand how information is represented and transformed within the hidden layers of a deep neural network.
Not ideal if you are a practitioner looking for tools to improve model performance, optimize training, or deploy models in production.
Stars
8
Forks
1
Language
Jupyter Notebook
License
BSD-3-Clause
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Priesemann-Group/nninfo"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sbi-dev/sbi
sbi is a Python package for simulation-based inference, designed to meet the needs of both...
SMTorg/smt
Surrogate Modeling Toolbox
reservoirpy/reservoirpy
A simple and flexible code for Reservoir Computing architectures like Echo State Networks
GPflow/GPflow
Gaussian processes in TensorFlow
thousandbrainsproject/tbp.monty
Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.