Random Neural Network Simulator implemented in Python.
Project description
Overview
Random Neural Network Simulator implemented in Python.
Setup
Requirements
- Python 3.6+
- NumPy
- Sklearn
Installation
Install this library directly into an activated virtual environment:
$ pip install rnnsim
or add it to your Poetry project:
$ poetry add rnnsim
Usage
After installation, the package can either be used as:
from rnnsim.model import SequentialRNN
sequential_model = SequentialRNN([2, 2, 1])
sequential_model.compile()
sequential_model.fit(train_data=(X_train, y_train), epochs=50, metrics="acc")
print(sequential_model.score((X_test, y_test)))
or
from rnnsim.RNN import RNN
# define model connections
conn_plus = {
1: [3, 4], 2: [3, 4],
3: [5], 4: [5], 5: []}
conn_minus = {
1: [3, 4], 2: [3, 4],
3: [5], 4: [5], 5: []}
model = RNN(n_total=5, input_neurons=2, output_neurons=1, conn_plus=conn_plus, conn_minus=conn_minus)
model.fit(epochs=N_Iterations, train_data=(X, Y))
References
- E. Gelenbe, Random neural networks with negative and positive signals and product form solution," Neural Computation, vol. 1, no. 4, pp. 502-511, 1989.
- E. Gelenbe, Stability of the random neural network model," Neural Computation, vol. 2, no. 2, pp. 239-247, 1990.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
rnnsim-0.1.tar.gz
(7.2 kB
view hashes)
Built Distribution
rnnsim-0.1-py3-none-any.whl
(7.7 kB
view hashes)