Explore Micrograd with Verso and PowerShell

Fri, 24 Jul 2026 00:00:00 +0000

Verso is an open-source interactive notebook platform and embeddable .NET execution engine. Its language kernels include PowerShell, C#, F#, Python, SQL, JavaScript, TypeScript, and HTTP, and it provides VS Code and browser front ends.

That timing is useful for PowerShell users. The.NET Interactive repository was archived in April 2026, leaving a gap for maintained multi-language .NET notebooks. Verso is an actively developed option with persistent kernel state, rich output, cross-language variable sharing, and headless notebook execution.

This post walks through anexperimental PowerShell micrograd notebook built for Verso. The sample was proposed separately and is not currently part of Verso’smain branch, so treat it as an exploration rather than a shipped Verso sample.

The notebook ports the core ideas from Andrej Karpathy’smicrograd to PowerShell. The original project is intentionally tiny: scalar-valued reverse-mode automatic differentiation, then a small neural-network library on top. Karpathy’s video,The spelled-out intro to neural networks and backpropagation: building micrograd, is effective because it does not hide the graph. The PowerShell version keeps that spirit, usingPSQuickGraph andPSGraphView to render the computation graph directly from objects created in the notebook.

The diagrams in this article were generated by PowerShell from the same helper scripts used by the notebook and exported as Graphviz SVG through PSGraphView.

Notebook Setup

1234dotnet tool install --global Verso.CliInstall-Module -Name PSQuickGraph -RequiredVersion2.5.0 -Scope CurrentUserInstall-Module -Name PSGraphView -RequiredVersion0.1.0 -Scope CurrentUser

12345git clone https://github.com/DataficationSDK/Verso.gitSet-Location ./Versogit checkout 3f8629154a28824ad5fbd0eaca49c3ef57168704verso serve ./samples/Notebooks/powershell/micrograd/micrograd-ps.verso

`12`	`Import-Module PSQuickGraphImport-Module PSGraphView`

. ./value.ps1. ./graphHelper.ps1. ./neuronHelper.ps1. ./helpers.ps1

 1 2 3 4 5 6 7 8 910static [Value] op_Addition([Value]$left, [Value]$right) {$out = [Value]::new($left.data +$right.data,@($left,$right),"+","+_res")$out.backward = {$left.grad +=1 *$out.grad$right.grad +=1 *$out.grad }.GetNewClosure()return$out}

 1 2 3 4 5 6 7 8 910static [Value] op_Multiply([Value]$left, [Value]$right) {$out = [Value]::new($left.data *$right.data,@($left,$right),"*","*_res")$out.backward = {$left.grad +=$right.data *$out.grad$right.grad +=$left.data *$out.grad }.GetNewClosure()return$out}

 1 2 3 4 5 6 7 8 91011[Value] Tanh(){$v =$this$t = [Math]::Tanh($this.data)$out = [Value]::new($t,@($this),"tanh")$out.backward = {$v.grad += (1 - [Math]::Pow($t,2)) *$out.grad }.GetNewClosure()return$out}

1234567$a = [Value]::new(2.0,'a')$b = [Value]::new(-3.0,'b')$c = [Value]::new(10.0,'c')$e =$a *$b;$e.label ='e'$d =$e +$c;$d.label ='d'$f = [Value]::new(-2.0,'f')$L =$d *$f;$L.label ='L'

12$scalarGraph = New-ExpressionGraph -val$LShow-ExpressionGraph -Graph$scalarGraph

123456$bpGraph = New-BackpropagationGraph -val$L$L.grad =1.0Get-GraphTopologicalSort -Graph$bpGraph -Reverse | ForEach-Object {$_.OriginalObject } | ForEach-Object { &$_.backward }

 1 2 3 4 5 6 7 8 9101112$x1 = [Value]::new(2.0,'x1')$x2 = [Value]::new(0.0,'x2')$w1 = [Value]::new(-3.0,'w1')$w2 = [Value]::new(1.0,'w2')$b = [Value]::new(6.8813735870195432,'b')$x1w1 =$x1 *$w1;$x1w1.label ='x1*w1'$x2w2 =$x2 *$w2;$x2w2.label ='x2*w2'$x1w1x2w2 =$x1w1 +$x2w2;$x1w1x2w2.label ='x1*w1 + x2*w2'$n =$x1w1x2w2 +$b;$n.label ='n'$o =$n.Tanh();$o.label ='o'

123456$bpNeuronGraph = New-BackpropagationGraph -val$o$o.grad =1.0Get-GraphTopologicalSort -Graph$bpNeuronGraph -Reverse | ForEach-Object {$_.OriginalObject } | ForEach-Object { &$_.backward }

 1 2 3 4 5 6 7 8 9101112131415161718192021classNeuron { [Value[]]$w [Value]$b Neuron([int]$nin) {$this.w =for ($i =0;$i-lt$nin;$i++) { [Value]::new(([Random]::Shared.NextDouble() *2 -1),"w$i") }$this.b = [Value]::new(([Random]::Shared.NextDouble() *2 -1),"b") } [Value] Invoke([Value[]]$x) {$sum =$this.bfor ($i =0;$i-lt$this.w.Count;$i++) {$sum =$sum + ($this.w[$i] *$x[$i]) }return$sum.Tanh() }}

 1 2 3 4 5 6 7 8 9101112$x =@( [Value]::new(2.0,'x1') [Value]::new(3.0,'x2') [Value]::new(-1.0,'x3'))$layer = [Layer]::new(3,4)$layer.Invoke($x)$net = [MLP]::new(3,@(4,4,1))$res =$net.Invoke($x)$res

12$netGraph = New-ExpressionGraph -val$res[0]Show-ExpressionGraph -Graph$netGraph -rankdir'TD'

 1 2 3 4 5 6 7 8 910111213$xs =@(@([Value]::new(2.0,'x11'), [Value]::new(3.0,'x12'), [Value]::new(-1.0,'x13')),@([Value]::new(3.0,'x21'), [Value]::new(-1.0,'x22'), [Value]::new(0.5,'x23')),@([Value]::new(0.5,'x31'), [Value]::new(1.0,'x32'), [Value]::new(1.0,'x33')),@([Value]::new(1.0,'x41'), [Value]::new(1.0,'x42'), [Value]::new(-1.0,'x43')))$ys =@( [Value]::new(1.0,'y1'), [Value]::new(-1.0,'y2'), [Value]::new(-1.0,'y3'), [Value]::new(1.0,'y4'))

1234567$net = [MLP]::new(3,@(4,4,1))$ypred =$xs | ForEach-Object {$net.Invoke($_)[0] }$loss = Zip -Left$ys -Right$ypred | Sum-Value {$diff =$_.Right -$_.Left$diff *$diff}

 1 2 3 4 5 6 7 8 91011121314151617181920212223242526foreach ($pin$net.parameters()) {$p.grad =0.0}foreach ($rowin$xs) {foreach ($vin$row) {$v.grad =0.0 }}foreach ($yin$ys) {$y.grad =0.0}$ypred =$xs | ForEach-Object {$net.Invoke($_)[0] }$loss = Zip -Left$ys -Right$ypred | Sum-Value {$diff =$_.Right -$_.Left$diff *$diff}$loss.grad =1.0$bpLossGraph = New-BackpropagationGraph -val$lossGet-GraphTopologicalSort -Graph$bpLossGraph -Reverse | ForEach-Object {$_.OriginalObject } | ForEach-Object { &$_.backward }foreach ($pin$net.parameters()) {$p.data +=-0.1 *$p.grad}

12$lossGraph = New-ExpressionGraph -val$lossShow-ExpressionGraph -Graph$lossGraph -rankdir'TD'

Articles from July 2026 on PowerShell.org - Welcome Automaters!

Explore Micrograd with Verso and PowerShell

Notebook Setup

Validate Azure Resource Relationships with PSRule and PowerShell Graphs

Why per-resource rules are not enough

Articles from July 2026 on PowerShell.org - Welcome Automaters!

Explore Micrograd with Verso and PowerShell

Notebook Setup

Scalar Computation Graph

Backpropagation Order

One Neuron

Layer and MLP

Training Data and Loss

One Training Step

Training Loop

Why This Matters