/* ------------------------------------ */
void test_gaussian_noise_computation(void)
/* ------------------------------------ */
{
int i;
int n = 10000;
float32 x, sx, sxx;
sx = 0.0f; sxx = 0.0f;
for(i=0; i<n; i++) {
x = gaussian_noise(0, 10);
//printf("%10.4f\n", x);
sx += x;
sxx += x*x;
}
printf("average = %10.4f sigma = %10.4f\n", sx/n, calc_sigma(n, sx, sxx));
sx = 0.0f; sxx = 0.0f;
for(i=0; i<n; i++) {
x = gaussian_noise(0, 20);
//printf("%10.4f\n", x);
sx += x;
sxx += x*x;
}
printf("average = %10.4f sigma = %10.4f\n", sx/n, calc_sigma(n, sx, sxx));
}
// ---------------------------------------
void test_gaussian_noise_computation(void)
// ---------------------------------------
{
// pour valider que le generateur aleatoire a bien
// les bons parametres statistiques ...
int i;
int n = 1000000;
float32 x, sx, sxx;
puts("-------------------------------------");
puts("-- test_gaussian_noise_computation --");
puts("-------------------------------------");
sx = 0.0f; sxx = 0.0f;
for(i = 0; i < n; i++) {
x = gaussian_noise(0, 10);
//printf("%10.4f\n", x);
sx += x;
sxx += x*x;
}
printf("average = %10.3f sigma = %10.3f\n", sx/n, calc_sigma(n, sx, sxx));
sx = 0.0f; sxx = 0.0f;
for(i = 0; i < n; i++) {
x = gaussian_noise(0, 20);
//printf("%10.4f\n", x);
sx += x;
sxx += x*x;
}
printf("average = %10.3f sigma = %10.3f\n", sx/n, calc_sigma(n, sx, sxx));
}
void back_propagation(){
int i,j,k;
for(i = LAYER_SIZE - 2; i > 0; i--){
for(j = 0; j < UNIT_SIZE; j++){
unit[i][j].sigma = calc_sigma(unit[i][j], j);
}
}
for(i = 1; i < LAYER_SIZE; i++){
for(j = 0; j < UNIT_SIZE; j++){
for(k = 0; k < UNIT_SIZE; k++){
double diff = unit[i][j].sigma * unit[i][j].input_unit[k].value;
unit[i][j].input_weight[k] = unit[i][j].input_weight[k] - LEARNING_PARAM * diff;
}
}
}
}
