NanoBrain/NanoBrain-unitypackage
NanoBrain/NanoBrain-unitypackage
2
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

Generic 1-layer training

Browse Source
This commit is contained in:
Pascal Serrarens 2026-07-03 11:44:58 +02:00
parent c16c3c5dc9
commit a38e4c3c77
2 changed files with 50 additions and 48 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

90
Runtime/Scripts/Core/Neuron.cs
View File

@ -706,65 +706,65 @@ namespace NanoBrain {
Debug.Log($"Updated weight: {loss.magnitude} {loss} {scaledOutput} {synapse.weight}");
}
public void BackPropagation1(Vector3 cost, Vector3 error, float learningRate) {
cost = Vector3.Scale(error, error); // error^2
float3 derivative = 2 * error; // derivative of (error^2)
// inverted because it uses the non-convential
// error=(actual-taget) instead of (target-actual)
// dSSR / dPredicted
// public void BackPropagation1(Vector3 cost, Vector3 error, float learningRate) {
// cost = Vector3.Scale(error, error); // error^2
// float3 derivative = 2 * error; // derivative of (error^2)
// // inverted because it uses the non-convential
// // error=(actual-taget) instead of (target-actual)
// // dSSR / dPredicted
// Bias
float3 deltaBias = derivative;
// deltaBias *= 1; // because bias is always fully applied
Vector3 stepSize = deltaBias * learningRate;
this.bias -= stepSize;
// // Bias
// float3 deltaBias = derivative;
// // deltaBias *= 1; // because bias is always fully applied
// Vector3 stepSize = deltaBias * learningRate;
// this.bias -= stepSize;
foreach (Synapse synapse in this.synapses) {
// derivative for the weight?
float3 deltaSynapse = derivative; // dSSR/dPredicted
// derivative for the previous activation
deltaSynapse *= synapse.neuron.activation; // dPredicted/dWeight
// foreach (Synapse synapse in this.synapses) {
// // derivative for the weight?
// float3 deltaSynapse = derivative; // dSSR/dPredicted
// // derivative for the previous activation
// deltaSynapse *= synapse.neuron.activation; // dPredicted/dWeight
// // derivative for the activator
// switch (activator) {
// case ActivationType.Linear:
// //delta2 *= 1;
// break;
// default:
// break;
// }
float deltaWeight = length(deltaSynapse);
synapse.weight += learningRate * deltaWeight;
// // // derivative for the activator
// // switch (activator) {
// // case ActivationType.Linear:
// // //delta2 *= 1;
// // break;
// // default:
// // break;
// // }
// float deltaWeight = length(deltaSynapse);
// synapse.weight += learningRate * deltaWeight;
synapse.neuron.BackPropagation2(derivative * synapse.weight, learningRate);
}
}
// synapse.neuron.BackPropagation2(derivative * synapse.weight, learningRate);
// }
// }
public void BackPropagation0(Vector3 error, float learningRate) {
float3 derivative = 2 * error; // derivative of (error^2)
public void BackPropagation0(float error, float learningRate) {
float derivative = 2 * error; // derivative of (error^2)
// inverted because it uses the non-convential
// error=(actual-taget) instead of (target-actual)
// dSSR / dPredicted
BackPropagation2(derivative, learningRate);
}
public void BackPropagation2(Vector3 derivative, float learningRate) {
public void BackPropagation2(float derivative, float learningRate) {
// Bias
float3 deltaBias = derivative; // dSSR/dActivator
switch (activator) { // dActivator/dBias
case ActivationType.Linear:
//deltaBias *= 1;
break;
default:
break;
}
// deltaBias *= 1; // because bias is always fully applied
Vector3 stepSize = deltaBias * learningRate;
this.bias -= stepSize;
// float3 deltaBias = derivative; // dSSR/dActivator
// switch (activator) { // dActivator/dBias
// case ActivationType.Linear:
// //deltaBias *= 1;
// break;
// default:
// break;
// }
// // deltaBias *= 1; // because bias is always fully applied
// Vector3 stepSize = deltaBias * learningRate;
// this.bias -= stepSize;
foreach (Synapse synapse in this.synapses) {
synapse.BackPropagation(length(derivative), learningRate);
synapse.BackPropagation(this, derivative, learningRate);
// // derivative for the weight?
// float3 deltaSynapse = derivative; // dSSR/dActivator
@ -785,7 +785,7 @@ namespace NanoBrain {
// float deltaWeight = length(deltaSynapse);
// synapse.weight += learningRate * deltaWeight;
BackPropagation2(derivative * synapse.weight, learningRate);
// BackPropagation2(derivative * synapse.weight, learningRate);
}
}

6
Runtime/Scripts/Core/Synapse.cs
View File

@ -33,13 +33,15 @@ namespace NanoBrain {
this.weight = weight;
}
public virtual void BackPropagation(float error, float learningRate) {
public virtual void BackPropagation(Neuron receiver, float error, float learningRate) {
float derivative = error;
switch (neuron.activator) {
switch (receiver.activator) {
case Neuron.ActivationType.Linear:
derivative *= 1;
break;
default:
Debug.Log("other activator");
break;
}
derivative *= math.length(neuron.activation);