Feed Forward Neural Networks
Project description
Installation
$ [sudo] pip install feedforwardnet-shine7
Usage
from Neural_Network import NeuralNetwork
# Create a Neural Network
inputs = 2
output_neurons = 1
hidden_layers = 2
each_hidden_nodes = [2, 3]
network = NeuralNetwork(inputs, hidden_layers, output_neurons, each_hidden_nodes)
Building a dataset
Dataset must be python list of data_samples, where each data_sample is a list of input and target.
For Eg: Input: [1, 1], Target: [1] => [[1, 1], [1]] is a data sample.
A typical XOR function's dataset looks something like :
>>> XOR_data =
[
[ ### ####
[0, 0], # Input Data
[0] # Output Sample
], ### ####
[
[0, 1],
[1]
],
[
[1, 0],
[1]
],
[
[1, 1],
[0]
]
]
>>> size = 4 # Length of the data
Training The network
The library provides a Train function which accepts the dataset, dataset size, and three optional parameters MAX_EPOCHS, graph, and log_outputs.
def Train(dataset, size, MAX_EPOCHS=10000, graph=False, log_outputs=True) :
....
....
For Eg: If you want to train your network for 5000 epochs and display epoch vs error graph after training.
>>> network.Train(XOR_data, size, MAX_EPOCHS=5000, graph=True)
Notice that I didn't change the value of log_outputs as I want the output to printed for each epoch.
Debugging
If you want to look at the network's weights at any point of time, the library provides a print_weights function.
>>> network.print_weights()
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for feedforwardnet-shine7-0.0.4.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7cc6d3d887810aca4fed18d0a9debee2d184a873c91e88c0088e440ad398050b |
|
MD5 | 464cd4ca1452751282f61d9a5e566149 |
|
BLAKE2b-256 | 78c8181009a93b845d92c472648ac51119e43c8774c0abe2a6595af0bc1c5213 |
Hashes for feedforwardnet_shine7-0.0.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cf88248d5552c6bea092fe73079b2f3081e97e5cff7118da28df275ae94caed5 |
|
MD5 | d40f591368664b1b1c3acbecbf56db9c |
|
BLAKE2b-256 | 72aed1d28bad822fc3d58704735ccc5f66e9c559b6c14b5613af9e8a4f40c03f |