Neural network library on Keras
Project description
# conx
Neural Network Library for Cognitive Scientists
Built in Python on Keras
[](https://circleci.com/gh/Calysto/conx/tree/master) [](https://codecov.io/gh/Calysto/conx)
Networks implement neural network algorithms. Networks can have as many hidden layers as you desire.
The network is specified to the constructor by providing sizes. For example, Network("XOR", 2, 5, 1) specifies a network named "XOR" with a 2-node input layer, 5-unit hidden layer, and a 1-unit output layer.
## Example
Computing XOR via a target function:
```python
from conx import Network, SGD
dataset = [[[0, 0], [0]],
[[0, 1], [1]],
[[1, 0], [1]],
[[1, 1], [0]]]
net = Network("XOR", 2, 2, 1, activation="sigmoid")
net.set_dataset(dataset)
net.compile(loss='mean_squared_error',
optimizer=SGD(lr=0.3, momentum=0.9))
net.train(2000, report_rate=10, accuracy=1)
net.test()
```
## Install
```shell
pip install conx -U
```
You will need to decide whether to use Theano or Tensorflow. Pick one:
```shell
pip install theano
```
or
```shell
pip install tensorflow
```
To use Theano as the Keras backend rather than TensorFlow, edit (or create) `~/.keras/kerson.json` to:
```json
{
"backend": "theano",
"image_data_format": "channels_last",
"epsilon": 1e-07,
"floatx": "float32"
}
```
## Examples
See the examples and notebooks folders for additional examples.
Neural Network Library for Cognitive Scientists
Built in Python on Keras
[](https://circleci.com/gh/Calysto/conx/tree/master) [](https://codecov.io/gh/Calysto/conx)
Networks implement neural network algorithms. Networks can have as many hidden layers as you desire.
The network is specified to the constructor by providing sizes. For example, Network("XOR", 2, 5, 1) specifies a network named "XOR" with a 2-node input layer, 5-unit hidden layer, and a 1-unit output layer.
## Example
Computing XOR via a target function:
```python
from conx import Network, SGD
dataset = [[[0, 0], [0]],
[[0, 1], [1]],
[[1, 0], [1]],
[[1, 1], [0]]]
net = Network("XOR", 2, 2, 1, activation="sigmoid")
net.set_dataset(dataset)
net.compile(loss='mean_squared_error',
optimizer=SGD(lr=0.3, momentum=0.9))
net.train(2000, report_rate=10, accuracy=1)
net.test()
```
## Install
```shell
pip install conx -U
```
You will need to decide whether to use Theano or Tensorflow. Pick one:
```shell
pip install theano
```
or
```shell
pip install tensorflow
```
To use Theano as the Keras backend rather than TensorFlow, edit (or create) `~/.keras/kerson.json` to:
```json
{
"backend": "theano",
"image_data_format": "channels_last",
"epsilon": 1e-07,
"floatx": "float32"
}
```
## Examples
See the examples and notebooks folders for additional examples.
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
conx-3.0.1.tar.gz
(20.8 kB
view details)
Built Distribution
conx-3.0.1-py2.py3-none-any.whl
(23.4 kB
view details)
File details
Details for the file conx-3.0.1.tar.gz.
File metadata
- Download URL: conx-3.0.1.tar.gz
- Upload date:
- Size: 20.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 55b2f4d5f9323c5753a88124ed6bba72c8cc8ebd55edc2413aea05a45b30099e |
|
| MD5 | 75a75edc8b98dad4702515025b283a4a |
|
| BLAKE2b-256 | 3646e7106b30479c55347cfbc7a61b029c6825cc38f5da1fa98cbf34746314b5 |
File details
Details for the file conx-3.0.1-py2.py3-none-any.whl.
File metadata
- Download URL: conx-3.0.1-py2.py3-none-any.whl
- Upload date:
- Size: 23.4 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 7038e17705912ec54d9aa439dcc05c32a58362c187e65b219d08ee58e73a2b38 |
|
| MD5 | 499f5a9b5677a50985231ae05ee2ecd8 |
|
| BLAKE2b-256 | a18a8091dc5d31329bb8295e1ce45de2fdd504ff8f986e48ea24215b66faea67 |
