Neural network library on Theano
Project description
# conx
Neural network library in Python built on Theano
Computing a target on the fly:
```
from conx import Network
inputs = [[0, 0],
[0, 1],
[1, 0],
[1, 1]]
def xor(inputs):
a = inputs[0]
b = inputs[1]
return [int((a or b) and not(a and b))]
net = Network(2, 2, 1)
net.set_inputs(inputs)
net.set_target_function(xor)
net.train()
net.test()
```
Given a specified target:
```
from conx import Network
inputs = [[0,0], [0,1], [1,0], [1,1]]
net = Network(2, 2, 1)
net.set_inputs(inputs)
net.train()
net.test()
```
Neural network library in Python built on Theano
Computing a target on the fly:
```
from conx import Network
inputs = [[0, 0],
[0, 1],
[1, 0],
[1, 1]]
def xor(inputs):
a = inputs[0]
b = inputs[1]
return [int((a or b) and not(a and b))]
net = Network(2, 2, 1)
net.set_inputs(inputs)
net.set_target_function(xor)
net.train()
net.test()
```
Given a specified target:
```
from conx import Network
inputs = [[0,0], [0,1], [1,0], [1,1]]
net = Network(2, 2, 1)
net.set_inputs(inputs)
net.train()
net.test()
```
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 Distributions
conx-0.2.0.zip
(11.2 kB
view hashes)
conx-0.2.0.tar.gz
(7.7 kB
view hashes)
Built Distribution
conx-0.2.0-py3-none-any.whl
(10.2 kB
view hashes)