nn4n 1.0.2

Neural Networks for Neuroscience Research

NN4N: Neural Networks for Neuroscience

Some of the most commonly used neural networks in neuroscience research are included in this project to ease the implementation process.

GitHub

Table of contents

• Install
  • Install From GitHub
• Model
  • CTRNN (Continuous-Time RNN)
• Structure
  • Multi-Area
  • Multi-Area with E/I constraints
  • Random Input

Install

Install using pip

pip install nn4n

Install from GitHub

git clone https://github.com/zhaozewang/NN4Neurosci.git

Install using command line

cd NN4Neurosci/
python setup.py install

Install using pip

cd NN4Neurosci/
pip install .

Model

CTRNN

The implementation of standard continuous-time RNN (CTRNN). This implementation supports enforcing sparsity constraint (i.e. preventing new synapses from being created) and E/I constraints (i.e. enforcing Dale's law).

• Documentation
• Examples

Structure

The detailed structure (e.g. whether its modular or hierarchical etc.) of any standard 3-layer RNN (as shown in figure above) can be specified using masks in our model module implementation. Easy implementations of a few RNN structures is included in the structure module.

• Documentation

Multi-Area

The HiddenLayer of a RNN is often defined using a connectivity matrix, depicting a somewhat 'random' connectivity between neurons. The connectivity matrix is often designed to imitate the connectivity of a certain brain area or a few brain areas. When modeling a single brain area, the connectivity matrix is often a fully connected matrix.
However, to model multiple brain areas, it would be more reasonable to use a connectivity matrix with multiple areas. In each areas is densely connected within itself and sparsely connected between areas. The MultiArea class in the structure module is designed to implement such a connectivity matrix.

• Examples

Multi-Area with E/I constraints

On top of modeling brain with multi-area hidden layer, another critical constraint would be the Dale's law, as proposed in the paper Training Excitatory-Inhibitory Recurrent Neural Networks for Cognitive Tasks: A Simple and Flexible Framework by Song et al. 2016. The MultiAreaEI class in the structure module is designed to implement such a connectivity matrix.
This class allows for a much easier implementation of the E/I constraints particularly when there are multiple areas in the hidden layer. It provides flexible control over the excitatory-excitatory, excitatory-inhibitory, inhibitory-excitatory, and inhibitory-inhibitory connections on top of the basic MultiArea features.

• Examples

Random Input

Neurons's dynamic receiving input will be heavily driven by the inputting signal. Injecting signal to only part of the neuron will result in more versatile and hierarchical dynamics. See A Versatile Hub Model For Efficient Information Propagation And Feature Selection

• Example to be added

Criterion

RNNLoss

The loss function is modularized. The RNNLoss class is designed in modular fashion and included the most commonly used loss functions in neuroscience research.

• Documentation

Others

For similar projects:

• nn-brain

Acknowledgements

Immense thanks to Christopher J. Cueva for his mentorship in developing this project. This project can't be done without his invaluable help.