**Gorgonia**works like similar frameworks, for example,

**Tensorflow**, allowing the creation of

**graphs**of operations and

**tensors**.

The programming is a little low level, because we have to create the graphs containing the operations and the tensors, so there is no concept of **neuron** or **layers**, which exists in other frameworks.

## Installation

First, we have to install the necessary libraries. Oh, and for starters, your **Go** environment has to be 1.12 or higher!

```
$ go version
go version go1.13.5 linux/amd64
```

Then, install dependency packages:

`go get gorgonia.org/gorgonia`

There are very useful packages, such as:

But in this example I will use only **gorgonia**.

## The example

I will create a two layered network, like the model:

**bias**, which may make the network take a little longer to converge, but a better model It would be like this:

We have an input sequence of 4 pairs of numbers: {1,0}, {0,1}, {1,1}, {0,0}, with **shape** 4.2 (four lines and two columns). They are two input nodes, with four repetitions.

**hidden layer**of 2 nodes, so we will have a weight matrix with

**shape**2.2 (two rows and two columns), between the inputs and the hidden layer.

And we have an exit node, so we have a weight column with **shape** 2.

The expected result of a **XOR** operation would be as follows: {1,1,0,0}.

## Model Assembly and Training

**example file**imports the required libraries. I will start with the interesting part, which is to create a struct to represent our neural network model:

```
type nn struct {
g *ExprGraph
w0, w1 *Node
pred *Node
predVal Value
}
```

This struct contains pointers to the operations graph (g), the weight layer nodes (w0 – input / hidden and w1 – hidden / output), the output node (pred) and its value (predVal).

**learnables**, what the model is expected to learn. This makes the

**Backpropagation**part much easier:

```
func (m *nn) learnables() Nodes {
return Nodes{m.w0, m.w1}
}
```

**factory method**to instantiate the neural network:

```
func newNN(g *ExprGraph) *nn {
// Create node for w/weight
w0 := NewMatrix(g, dt, WithShape(2, 2), WithName("w0"), WithInit(GlorotN(1.0)))
w1 := NewMatrix(g, dt, WithShape(2, 1), WithName("w1"), WithInit(GlorotN(1.0)))
return &nn{
g: g,
w0: w0,
w1: w1}
}
```

Here we create two gorgonia matrices, informing their **shapes** and initializing with random numbers (using the Glorot algorithm).

We’re just creating nodes in the graph! Nothing will really be performed by **gorgonia**!

**Forward propagation**that takes the input array and passes the elements across the network:

```
func (m *nn) fwd(x *Node) (err error) {
var l0, l1, l2 *Node
var l0dot, l1dot *Node
// Camada de input
l0 = x
// Multiplicação pelos pesos e sigmoid
l0dot = Must(Mul(l0, m.w0))
// Input para a hidden layer
l1 = Must(Sigmoid(l0dot))
// Multiplicação pelos pesos:
l1dot = Must(Mul(l1, m.w1))
// Camada de saída:
l2 = Must(Sigmoid(l1dot))
m.pred = l2
Read(m.pred, &m.predVal)
return nil
}
```

**Sigmoid**and move to the hidden layer, reaching the end.

Finally, in the **main()** method we instantiate our input vector and our result vector:

```
// Set input x to network
xB := []float64{1,0,0,1,1,1,0,0}
xT := tensor.New(tensor.WithBacking(xB), tensor.WithShape(4, 2))
x := NewMatrix(g,
tensor.Float64,
WithName("X"),
WithShape(4, 2),
WithValue(xT),
)
// Define validation data set
yB := []float64{1, 1, 0, 0}
yT := tensor.New(tensor.WithBacking(yB), tensor.WithShape(4, 1))
y := NewMatrix(g,
tensor.Float64,
WithName("y"),
WithShape(4, 1),
WithValue(yT),
)
```

Append the **Forward pass** in the graph:

```
// Run forward pass
if err := m.fwd(x); err != nil {
log.Fatalf("%+v", err)
}
```

**MSE**:

```
// Calculate Cost w/MSE
losses := Must(Sub(y, m.pred))
square := Must(Square(losses))
cost := Must(Mean(square))
```

And append the gradient and **Backpropagation** in the graph:

```
// Do Gradient updates
if _, err = Grad(cost, m.learnables()...); err != nil {
log.Fatal(err)
}
```

Finally, instantiate a **gorgonia** virtual machine and run the graph:

```
// Instantiate VM and Solver
vm := NewTapeMachine(g, BindDualValues(m.learnables()...))
solver := NewVanillaSolver(WithLearnRate(0.1))
for i := 0; i < 10000; i++ {
vm.Reset()
if err = vm.RunAll(); err != nil {
log.Fatalf("Failed at inter %d: %v", i, err)
}
solver.Step(NodesToValueGrads(m.learnables()))
vm.Reset()
}
fmt.Println("nnOutput after Training: n", m.predVal)
```

I repeated the training many times running the graph with **vm.RunAll()**.

This is the training result:

```
Output after Training:
C[ 0.6267103873881292 0.6195071561964745 0.47790055401989834 0.3560452019123115]
```

You can create any neural network model with **Gorgonia**. This is just a kickstart. I didn’t worry about regularization and performance, but that’s a topic for another post!

Cleuton Sampaio, M.Sc.