Naaturel/ANN-framework
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Implement multi layer

Browse Source
This commit is contained in:
Laurent
2026-03-30 13:38:44 +02:00
parent b36a900f87
commit aed78fe9d2
13 changed files with 153 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
src/main/java/com/naaturel/ANN/Main.java
View File

@@ -3,6 +3,7 @@ package com.naaturel.ANN;
import com.naaturel.ANN.domain.model.neuron.Neuron;
import com.naaturel.ANN.domain.abstraction.Trainer;
import com.naaturel.ANN.implementation.multiLayers.Sigmoid;
import com.naaturel.ANN.implementation.multiLayers.TanH;
import com.naaturel.ANN.implementation.training.GradientBackpropagationTraining;
import com.naaturel.ANN.infrastructure.dataset.DataSet;
import com.naaturel.ANN.infrastructure.dataset.DatasetExtractor;
@@ -14,33 +15,36 @@ public class Main {
public static void main(String[] args){
int nbrInput = 2;
int nbrClass = 3;
int nbrInput = 25;
int nbrClass = 4;
int nbrLayers = 2;
int[] neuronPerLayer = new int[]{10, nbrClass};
DataSet dataset = new DatasetExtractor()
.extract("C:/Users/Laurent/Desktop/ANN-framework/src/main/resources/assets/table_3_1.csv", nbrClass);
.extract("C:/Users/Laurent/Desktop/ANN-framework/src/main/resources/assets/table_3_5.csv", nbrClass);
List<Layer> layers = new ArrayList<>();
for(int i = 0; i < nbrLayers; i++){
for (int i = 0; i < neuronPerLayer.length; i++){
List<Neuron> neurons = new ArrayList<>();
for (int j=0; j < nbrClass; j++){
for (int j = 0; j < neuronPerLayer[i]; j++){
int nbrSyn = i == 0 ? nbrInput: neuronPerLayer[i-1];
List<Synapse> syns = new ArrayList<>();
for (int k=0; k < nbrInput; k++){
syns.add(new Synapse(new Input(0), new Weight(0)));
for (int k=0; k < nbrSyn; k++){
syns.add(new Synapse(new Input(0), new Weight()));
}
Bias bias = new Bias(new Weight(0));
Bias bias = new Bias(new Weight());
Neuron n = new Neuron(syns, bias, new Sigmoid(1));
Neuron n = new Neuron(syns, bias, new TanH());
neurons.add(n);
}
Layer layer = new Layer(neurons);
layers.add(layer);
}
FullyConnectedNetwork network = new FullyConnectedNetwork(layers);
Trainer trainer = new GradientBackpropagationTraining();