https://github.com/wenyuzhao/multilayer-perceptron
Multilayer Perceptron based on NumPy
https://github.com/wenyuzhao/multilayer-perceptron
auto-encoder machine-learning neural-network stochastic-gradient-descent
Last synced: 8 months ago
JSON representation
Multilayer Perceptron based on NumPy
- Host: GitHub
- URL: https://github.com/wenyuzhao/multilayer-perceptron
- Owner: wenyuzhao
- License: apache-2.0
- Created: 2017-05-13T14:59:25.000Z (about 9 years ago)
- Default Branch: master
- Last Pushed: 2017-05-14T14:00:49.000Z (about 9 years ago)
- Last Synced: 2025-01-13T08:32:22.171Z (over 1 year ago)
- Topics: auto-encoder, machine-learning, neural-network, stochastic-gradient-descent
- Language: Python
- Size: 14.6 KB
- Stars: 2
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Multilayer Perceptron
[Multilayer Perceptron](https://en.wikipedia.org/wiki/Multilayer_perceptron) based on [NumPy](http://www.numpy.org/)
Using [Backpropagation](https://en.wikipedia.org/wiki/Backpropagation) with [Stochastic gradient descent](https://en.wikipedia.org/wiki/Stochastic_gradient_descent) to optimize network.
## Layers
* InputLayer
* TanhLayer
* SigmoidLayer
* ReLULayer
* LeakyReLULayer
* DropoutLayer
*See: [nn.py](nn.py)*
## Examples
See:
1. [Basic example](test.py)
2. [Auto encoder example](auto_encoder.py)
3. [Auto encoder & dropout example](auto_encoder_dropout.py)
## Auto encoder performance of [this example](auto_encoder.py)
```
input:
■
■ ■ ■ ■
■ ■ ■
■
■
prediction:
■
■ ■ ■
■ ■ ■
■
■
---------
input:
■
■
■ ■ ■ ■ ■
■ ■
■
prediction:
■
■
■ ■ ■ ■ ■
■
■
---------
input:
■
■
■ ■ ■
■ ■ ■ ■
■
prediction:
■
■
■ ■ ■
■ ■ ■
■
---------
input:
■
■
■ ■ ■ ■ ■
■
■ ■
prediction:
■
■
■ ■ ■ ■ ■
■
■
```