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

Move dataset components

Browse Source
This commit is contained in:
Laurent
2026-03-28 12:25:59 +01:00
parent 7fb4a7c057
commit 6d88651385
16 changed files with 47 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
src/main/java/com/naaturel/ANN/Main.java
View File

@@ -2,11 +2,10 @@ package com.naaturel.ANN;
import com.naaturel.ANN.domain.model.neuron.Neuron;
import com.naaturel.ANN.domain.abstraction.Trainer;
import com.naaturel.ANN.domain.model.dataset.DataSet;
import com.naaturel.ANN.domain.model.dataset.DatasetExtractor;
import com.naaturel.ANN.infrastructure.dataset.DataSet;
import com.naaturel.ANN.infrastructure.dataset.DatasetExtractor;
import com.naaturel.ANN.domain.model.neuron.*;
import com.naaturel.ANN.implementation.gradientDescent.Linear;
import com.naaturel.ANN.implementation.training.AdalineTraining;
import com.naaturel.ANN.implementation.training.GradientDescentTraining;
import java.util.*;
@@ -18,25 +17,31 @@ public class Main {
int nbrInput = 2;
int nbrClass = 3;
int nbrLayers = 1;
DataSet dataset = new DatasetExtractor()
.extract("C:/Users/Laurent/Desktop/ANN-framework/src/main/resources/assets/table_3_1.csv", nbrClass);
List<Neuron> neurons = new ArrayList<>();
List<Layer> layers = new ArrayList<>();
for(int i = 0; i < nbrLayers; i++){
for (int i=0; i < nbrClass; i++){
List<Synapse> syns = new ArrayList<>();
for (int j=0; j < nbrInput; j++){
syns.add(new Synapse(new Input(0), new Weight(0)));
List<Neuron> neurons = new ArrayList<>();
for (int j=0; j < nbrClass; j++){
List<Synapse> syns = new ArrayList<>();
for (int k=0; k < nbrInput; k++){
syns.add(new Synapse(new Input(0), new Weight(0)));
}
Bias bias = new Bias(new Weight(0));
Neuron n = new Neuron(syns, bias, new Linear());
neurons.add(n);
}
Bias bias = new Bias(new Weight(0));
Neuron n = new Neuron(syns, bias, new Linear());
neurons.add(n);
Layer layer = new Layer(neurons);
layers.add(layer);
}
Layer layer = new Layer(neurons);
Network network = new Network(List.of(layer));
Network network = new Network(layers);
Trainer trainer = new GradientDescentTraining();
trainer.train(network, dataset);