https://github.com/saran-nns/rmsorn

PyPi package of Reward-Modulated Self Organizing Recurrent Neural Network
https://github.com/saran-nns/rmsorn

artifical-intelligense brain-inspired-computing criticality deep-learning dynamical-modeling machine-learning neuroscience reinforcement-learning self-organizing-network spiking-cortical-model spiking-neural-networks

Last synced: 2 months ago
JSON representation

PyPi package of Reward-Modulated Self Organizing Recurrent Neural Network

• Host: GitHub
• URL: https://github.com/saran-nns/rmsorn
• Owner: Saran-nns
• License: mit
• Created: 2020-06-13T07:41:11.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T01:53:00.000Z (over 2 years ago)
• Last Synced: 2025-02-09T15:38:50.264Z (4 months ago)
• Topics: artifical-intelligense, brain-inspired-computing, criticality, deep-learning, dynamical-modeling, machine-learning, neuroscience, reinforcement-learning, self-organizing-network, spiking-cortical-model, spiking-neural-networks
• Language: Python
• Homepage:
• Size: 401 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
## Reward Modulated Self-Organizing Recurrent Neural Networks 

PyPi package of RM-SORN: a reward-modulated self-organizing recurrent neural network: [RMSORN-Paper](https://doi.org/10.3389/fncom.2015.00036)

[![Build Status](https://travis-ci.org/Saran-nns/rmsorn.svg?branch=master)](https://travis-ci.org/Saran-nns/rmsorn)

[![codecov](https://codecov.io/gh/Saran-nns/rmsorn/branch/master/graph/badge.svg)](https://codecov.io/gh/Saran-nns/rmsorn)

[![PyPI version](https://badge.fury.io/py/rmsorn.svg)](https://badge.fury.io/py/rmsorn)

[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://img.shields.io/github/license/Saran-nns/rmsorn)

#### To install the latest release:

```python

pip install rmsorn

```

The library is still in alpha stage, so you may also want to install the latest version from the development branch:

```python

pip install git+https://github.com/Saran-nns/rmsorn

```

#### Usage:

##### Update Network configurations

Navigate to home/conda/envs/ENVNAME/Lib/site-packages/rmsorn

or if you are unsure about the directory of rmsorn

Run

```python

import rmsorn

rmsorn.__file__

```

to find the location of the rmsorn package

Then, update/edit the configuration.ini

```python

from rmsorn.tasks import PatternRecognition

inputs, targets = PatternRecognitionTask.generate_sequence()

train_plast_inp_mat,X_all_inp,Y_all_inp,R_all, frac_pos_active_conn = SimulateRMSorn(phase = 'Plasticity', 

                                                                                      matrices = None,

                                                                                      inputs = np.asarray(inputs),sequence_length = 4, targets = targets,

                                                                                      reward_window_sizes = [1,5,10,20],

                                                                                      epochs = 1).train_rmsorn()

```

Notebook is avaialble at [RMSORN-Notebook](https://github.com/Saran-nns/PySORN_0.1/blob/master/v0.1.0/notebooks/alpha_cpu/RMSORN_pattern_recognition.ipynb)