virtual void backPropagate(vector<TensorBuf*>& deloutp, TensorBuf* delinp)
{
switch(engine)
{
case XSMM:
backPropagate(deloutp, delinp, 0);
break;
}
}
float
SentimentTraining::computeDerivatives(int startIndex, int endIndex) {
CudaInterface::fillParamMem(mModel.derivatives_d, 0);
for (int i = startIndex; i < endIndex; i++) {
forwardPropagate(mTrainTrees[i]);
}
for (int i = startIndex; i < endIndex; i++) {
backPropagate(mTrainTrees[i]);
}
return 1.0;
}
static void backPropagate_test( void ) {
float hiddenWeights[2][3] = {{-1, 1, 0}, {1, -1, 0}};
float outputWeights[2][3] = {{0.5, 0.25, 0}, {0.25, -0.5, 0}};
Node inputNodes[2];
Node hiddenNodes[2] = {{hiddenWeights[0]}, {hiddenWeights[1]}};
Node outputNode[2] = {{outputWeights[0]}, {outputWeights[1]}};
Node desired[2] = {{NULL, -0.5}, {NULL, -0.5}};
Layer inputLayer = {inputNodes, 2};
Layer hiddenLayer = {hiddenNodes, 2};
Layer outputLayer = {outputNode, 2};
Layer desiredLayer = {desired, 2};
inputLayer.nodes[0].output = 0.5; inputLayer.nodes[1].output = -0.5;
forwardPropagate( &inputLayer, &hiddenLayer, &outputLayer );
backPropagate( &hiddenLayer, &outputLayer, &desiredLayer );
assert( fabs( -0.3118693 - outputLayer.nodes[0].error ) < 0.001 && "First output node error is not as expected" );
assert( fabs( 0.0162368 - outputLayer.nodes[1].error ) < 0.001 && "Second output node error is not as expected" );
assert( fabs( -0.1518755 - hiddenLayer.nodes[0].error ) < 0.001 && "First node of hidden layer's output is not as expected" );
assert( fabs( -0.0860857 - hiddenLayer.nodes[1].error ) < 0.001 && "Second node of hidden layer's output is not as expected" );
}
void test_and_function()
{
int neurals[3];
long step=0, epochs, iSample=0;
BPNETWORK *nw = 0;
double input[4][2] = {{0,0},{0,1},{1,0},{1,1}};
double target[4][1] = {{0},{0},{0},{1}};
double e;
double *biases;
double threshold = 0.00001;
nw = (BPNETWORK *)malloc(sizeof(BPNETWORK));
epochs = 200000;
nw->learningRate = 0.15;
nw->alpha = 0.1;
biases = (double*)malloc(3 * sizeof(double));
biases[0] = 0.89;
biases[1] = -0.69;
biases[2] = 0.55;
printf("-------------Network configuration-------------\n");
printf("Epoch: %ld\n", epochs);
printf("LearningRate: %lf\n", nw->learningRate);
printf("Alpha(momentum): %lf \n", nw->alpha);
printf("Threshold: %lf \n", threshold);
printf("-----------------------------------------------\n");
if(nw != 0)
{
neurals[0] = 3;
neurals[1] = 3;
neurals[2] = 1;
initNetwork(biases, 3, neurals, nw);
step = 0;
do{
inputData(input[iSample], nw);
e = backPropagate(target[iSample], nw );
step = step + 1;
iSample = step % 4;
}while( (step<epochs) && e>threshold );
//printf("Mean square error: %lf (minimum error: %lf) (threshold: %lf) after %ld epoch\n", e, minE, threshold, count);
printf("Training completed with error/threshold %lf/%lf after %ld epochs \n\n", e, threshold, step);
//Test the network
printf("This network demonstrate for AND gate: \n");
inputData(input[0], nw);
feedForward(nw);
printf("Output(0,0): %lf\n", nw->layer[nw->nLayer-1].p[0].x);
inputData(input[1], nw);
feedForward(nw);
printf("Output(0,1): %lf\n", nw->layer[nw->nLayer-1].p[0].x);
inputData(input[2], nw);
feedForward(nw);
printf("Output(1,0): %lf\n", nw->layer[nw->nLayer-1].p[0].x);
inputData(input[3], nw);
feedForward(nw);
printf("Output(1,1): %lf\n", nw->layer[nw->nLayer-1].p[0].x);
release(nw);
free(nw);
free(biases);
}
}
int main()
{
double err;
int i, j, sample=0, iterations=0;
int sum = 0;
out = fopen("stats.txt", "w");
/* Seed the random number generator */
srand( time(NULL) );
assignRandomWeights();
while (1) {
if (++sample == MAX_SAMPLES) sample = 0;
inputs[0] = samples[sample].health;
inputs[1] = samples[sample].knife;
inputs[2] = samples[sample].gun;
inputs[3] = samples[sample].enemy;
target[0] = samples[sample].out[0];
target[1] = samples[sample].out[1];
target[2] = samples[sample].out[2];
target[3] = samples[sample].out[3];
feedForward(0);
/* need to iterate through all ... */
err = 0.0;
for (i = 0 ; i < OUTPUT_NEURONS ; i++) {
err += sqr( (samples[sample].out[i] - actual[i]) );
}
err = 0.5 * err;
fprintf(out, "%g\n", err);
printf("mse = %g\n", err);
if (iterations++ > 100000) break;
backPropagate();
}
printf("wih\n");
for (j = 0; j < HIDDEN_NEURONS; j++){
for (i = 0; i < INPUT_NEURONS+1; i++){
printf("%lf, ", wih[i][j]);
}
printf("\n");
}
printf("who\n");
for (j = 0; j < OUTPUT_NEURONS; j++){
for (i = 0; i < HIDDEN_NEURONS+1; i++){
printf("%lf, ", who[i][j]);
}
printf("\n");
}
/* Test the network */
for (i = 0 ; i < MAX_SAMPLES ; i++) {
inputs[0] = samples[i].health;
inputs[1] = samples[i].knife;
inputs[2] = samples[i].gun;
inputs[3] = samples[i].enemy;
target[0] = samples[i].out[0];
target[1] = samples[i].out[1];
target[2] = samples[i].out[2];
target[3] = samples[i].out[3];
feedForward(0);
if (action(actual) != action(target)) {
printf("%2.1g:%2.1g:%2.1g:%2.1g %s (%s)\n",
inputs[0], inputs[1], inputs[2], inputs[3],
strings[action(actual)], strings[action(target)]);
} else {
sum++;
}
}
printf("Network is %g%% correct\n",
((float)sum / (float)MAX_SAMPLES) * 100.0);
/* Run some tests */
/* Health Knife Gun Enemy */
inputs[0] = 2.0; inputs[1] = 1.0; inputs[2] = 1.0; inputs[3] = 1.0;
feedForward(0);
printf("2111 Action %s\n", strings[action(actual)]);
inputs[0] = 1.0; inputs[1] = 1.0; inputs[2] = 1.0; inputs[3] = 2.0;
feedForward(0);
printf("1112 Action %s\n", strings[action(actual)]);
inputs[0] = 0.0; inputs[1] = 0.0; inputs[2] = 0.0; inputs[3] = 0.0;
feedForward(0);
printf("0000 Action %s\n", strings[action(actual)]);
inputs[0] = 0.0; inputs[1] = 1.0; inputs[2] = 1.0; inputs[3] = 1.0;
feedForward(0);
printf("0111 Action %s\n", strings[action(actual)]);
inputs[0] = 2.0; inputs[1] = 0.0; inputs[2] = 1.0; inputs[3] = 3.0;
feedForward(0);
printf("2013 Action %s\n", strings[action(actual)]);
inputs[0] = 2.0; inputs[1] = 1.0; inputs[2] = 0.0; inputs[3] = 3.0;
feedForward(0);
printf("2103 Action %s\n", strings[action(actual)]);
inputs[0] = 0.0; inputs[1] = 1.0; inputs[2] = 0.0; inputs[3] = 3.0;
feedForward(0);
printf("0103 Action %s\n", strings[action(actual)]);
fclose(out);
return 0;
}
