neural-network-rs
| Crates.io | neural-network-rs |
| lib.rs | neural-network-rs |
| version | 0.1.4 |
| source | src |
| created_at | 2022-10-14 14:24:13.616982 |
| updated_at | 2022-10-14 15:32:02.087605 |
| description | A neural network library |
| homepage | |
| repository | https://github.com/ManuelLerchner/neural-network-rs |
| max_upload_size | |
| id | 688214 |
| size | 1,976,161 |
(ManuelLerchner)
documentation
README
Neural-Network
A simple neural network written in rust.
About
This implementation of a neural network using gradient-descent is completely written from ground up using rust. It is possible to specify the shape of the network, as well as the learning-rate of the network. Additionally, you can choose from one of many predefined datasets, for example the XOR- and CIRCLE Datasets, which represent the relative functions inside the union-square. As well as more complicated datasets like the RGB_DONUT, which represents a donut-like shape with a rainbow like color transition.
Below, you can see a training process, where the network is trying to learn the color-values of the RGB_DONUT dataset.
Features
The following features are currently implemented:
- Optimizers
- Adam
- RMSProp
- SGD
- Loss Functions
- Quadratic
- Activation Functions
- Sigmoid
- ReLU
- Layers
- Dense
- Plotting
- Plotting the cost-history during training
- Plotting the final predictions inside, either in grayscale or RGB
Usage
The process of creating and training the neural network is pretty straightforwards:
Example Training Process
Below, you can see how the network learns:
Learning Animation
Final Result
Cool training results
RGB_DONUT
Big Network
Small Network
XOR_PROBLEM
