c++ - Perceptron converging but returning odd results -

i made simple perceptron in c++ study ai , following book(pt_br) not make perceptron return expected result, tryed debug , find error didnt succeed.

my algorithm , gate results (a , b = y):

0 && 0 = 0  0 && 1 = 1 1 && 0 = 1 1 && 1 = 1 

basically working or gate or random.

i tried jump peter norving , russel book, goes fast on , dont explain on depth 1 perceptron training.

i want learn every inch of content, dont want jump multilayer perceptron without making simple 1 work, can help?

the following code minimal code operation explanations:

sharp function:

int signal(float &sin){     if(sin < 0)         return 0;     if(sin > 1)         return 1;      return round(sin);  } 

perceptron struct (w weights):

struct perceptron{     float w[3]; }; 

perceptron training:

perceptron starttraining(){     //- random factory generator     long int t = static_cast<long int>(time(null));     std::mt19937 gen;     gen.seed(std::random_device()() + t);     std::uniform_real_distribution<float> dist(0.0, 1.0);     //--      //-- samples (-1 | x | y)     float t0[][3] = {{-1,0,0},                      {-1,0,1},                      {-1,1,0},                      {-1,1,1}};      //-- expected result     short d [] = {0,0,0,1};      perceptron per;      per.w[0] = dist(gen);     per.w[1] = dist(gen);     per.w[2] = dist(gen);      //-- print random numbers     cout <<"init "<< "w0: " << per.w[0]  <<" w1: " << per.w[1] << " w2: " << per.w[2] << endl;      const float n = 0.1; // lerning rate n     int saida =0;        // output y     long int epo = 0;    // simple couter     bool erro = true;    // loop control      while(erro){         erro = false;         (int amost = 0; amost < 4; ++amost) {           // repeat number of samples x0=-1, x1,x2             float u=0;                                      // variable somatory             (int entrad = 0; entrad < 3; ++entrad) {    // repeat every sinaptic weight w0=θ , w1, w2                 u = u + (per.w[entrad] * t0[amost][entrad]);// u <- weights * inputs             }             // u=u-per.w[0];                                // references sau take θ , subtract u, tried without success             saida = signal(u);                              // returns 1 or 0             cout << d[amost] << " <- esperado | encontrado ->   "<< saida<< endl;             if(saida != d[amost]){                          // if output not equal expected value                 (int ajust = 0; ajust < 3; ++ajust) {                     per.w[ajust] = per.w[ajust] + n * (d[amost] - saida) * t0[amost][ajust]; // w <- w + ɳ * ((d - y) x)                     erro = true;                                                             // w: weights, ɳ: learning rate                 }                                                                            // d: desired outputs, y: outputs             }                                                                                // x: samples             epo++;          }     }     cout << "epocas(loops): " << epo << endl;     return per; } 

main testing part:

int main() {     perceptron per = starttraining();     cout << "fim" << endl;     cout << "w0: " << per.w[0]  <<" w1: " << per.w[1] << " w2: " << per.w[2] << endl;     while(true){         int x,y;         cin >> x >> y;          float u=0;         u = (per.w[1] * x);         u = u + (per.w[2] * y);         //u=u-per.w[0];          cout << signal(u) << endl;   }     return 0; } 

in main(), re-enable line commented out. alternatively, write make more illuminating:

float u = 0.0f;  u += (per.w[0] * float (-1)); u += (per.w[1] * float (x)); u += (per.w[2] * float (y)); 

the thing trained perceptron 3 inputs, first being hard-wired "-1" (making first weight w[0] act constant "bias"). accordingly, in training function, u sum of 3 of weight-input product. however, in main() posted, omit w[0] completely, producing wrong result.