gonn
GoNN
Description
Neural network library for go.
Visuals
Installation
go get -u github.com/teratron/gonn
Usage
package main
import "github.com/teratron/gonn/pkg/nn"
func main() {
// New returns a new neural network
// instance with the default parameters.
n := nn.New()
// Dataset.
input := []float64{.27, .31}
target := []float64{.7}
// Training dataset.
_, _ = n.Train(input, target)
}
Documentation
Properties of Perceptron Neural Network
Name
Neural network architecture name (required field for a config).
Bias
The neuron bias, false or true (required field for a config).
HiddenLayer
Array of the number of neurons in each hidden layer.
ActivationMode
ActivationMode function mode (required field for a config).
| Code | Activation | Description |
|---|---|---|
| 0 | LINEAR | Linear/identity |
| 1 | RELU | ReLu (rectified linear unit) |
| 2 | LEAKYRELU | Leaky ReLu (leaky rectified linear unit) |
| 3 | SIGMOID | Logistic, a.k.a. sigmoid or soft step |
| 4 | TANH | TanH (hyperbolic tangent) |
LossMode
The mode of calculation of the total error.
| Code | Loss | Description |
|---|---|---|
| 0 | MSE | Mean Squared Error |
| 1 | RMSE | Root Mean Squared Error |
| 2 | ARCTAN | Arctan |
| 3 | AVG | Average |
LossLimit
Minimum (sufficient) limit of the average of the error during training.
Rate
Learning coefficient (greater than 0.0 and less than or equal to 1.0).
More documentation is available at the gonn website or on pkg.go.dev.
Examples
You can find examples of neural networks in the example’s directory.
Support
Roadmap
Contributing
Authors and acknowledgment
License
Project status
Project at the initial stage.
See the latest commits.