68. Cameral sandwiches + AAI Lucy

Part: VII · Apps
Package: github.com/openfluke/welvet/layers/parallel
Status: ok — ✅ cameral

When

Building or training a net that needs the layers/parallel Op (also usable as a Parallel cam).

Where

import "github.com/openfluke/welvet/layers/parallel"

cd 68-cameral && source ../env.sh && go run .

Why

A single Dense chain cannot host two independent weight copies that share an input, merge, and optionally train under different updates. That is the cameral graph: hemispheres, not screen-space sprites and not a second hidden size.

What

Hemispheres / Bicameral / Sandwich / Mix. Stem → Parallel mid → Dense head. SetBranchModes + TrainStackMSE. Lucy races in AAI (test41 / test48 / test50) import this API; measuring is lucy/; harness is not engine.

Sample output (captured)

mix loss 0 err <nil>

Live capture from go run ./cmd/runall on local ../../welvet (exit 0).

Source

Copied from the Welvet feature book examples (openfluke.github.io/welvet/examples/68-cameral).

main.go

Download source ↓

package main

import (
	"fmt"

	"github.com/openfluke/welvet/core"
	"github.com/openfluke/welvet/layers/parallel"
	"github.com/openfluke/welvet/quant"
)

func main() {
	s, err := parallel.Bicameral(8, 16, 1, core.ActivationLeakyReLU,
		core.DTypeFloat32, quant.FormatNone)
	if err != nil {
		panic(err)
	}
	hemi := s.Children[1].(*parallel.Layer)
	hemi.SetBranchModes(parallel.ModeStepBP, parallel.ModeTweenSplitFastProxy)

	x := core.NewTensor[float32](1, 8)
	t := core.NewTensor[float32](1, 1)
	t.Data[0] = 0.5
	loss, err := parallel.TrainStackMSE(s, x, t, parallel.ModeStepBP, 0.01)
	fmt.Println("mix loss", loss, "err", err)
}