NeuralNet::NeuralNet(size_t no_inputs, size_t no_hidden, size_t no_outputs, ActivationFunc& hidden_act, ActivationFunc& output_act)
{
NNLayer hidden_layer(no_inputs, no_hidden, hidden_act);
NNLayer output_layer(no_hidden, no_outputs, output_act);
add_layer(hidden_layer);
add_layer(output_layer);
}
void TestWeightMatrix_Backward() {
double epsilon = 1e-3;
int n_outputs = 2;
int n_inputs = 3;
InputLayer input_layer(n_inputs);
OutputLayer output_layer(n_outputs);
WeightMatrix weights(input_layer, output_layer);
weights.set(0, 0, 0.5);
weights.set(1, 0, -2.0);
weights.set(2, 0, 1.5);
weights.set(0, 1, 1.0);
weights.set(1, 1, 0.7);
weights.set(2, 1, -1.0);
weights.setBias(0, 0.8);
weights.setBias(1, -0.3);
std::vector<double> inputs;
inputs.push_back(-2.0);
inputs.push_back(1.0);
inputs.push_back(3.0);
input_layer.receiveInput(inputs);
std::vector<double> transition = weights.fire(input_layer);
output_layer.receiveInput(transition);
assert(output_layer.getInput(0) == 2.3);
assert(output_layer.getInput(1) == -4.6);
// backpropagation step
std::vector<double> actual_outputs;
actual_outputs.push_back(1.0);
actual_outputs.push_back(1.0);
output_layer.computeGradient(actual_outputs);
weights.computeGradient(input_layer, output_layer);
assert(weights.getPartialDerivative(0, 0) > -1.3 - epsilon &&
weights.getPartialDerivative(0, 0) < -1.3 + epsilon);
assert(weights.getPartialDerivative(1, 0) > 0.65 - epsilon &&
weights.getPartialDerivative(1, 0) < 0.65 + epsilon);
assert(weights.getPartialDerivative(2, 0) > 1.95 - epsilon &&
weights.getPartialDerivative(2, 0) < 1.95 + epsilon);
assert(weights.getPartialDerivative(0, 1) > 5.6 - epsilon &&
weights.getPartialDerivative(0, 1) < 5.6 + epsilon);
assert(weights.getPartialDerivative(1, 1) > -2.8 - epsilon &&
weights.getPartialDerivative(1, 1) < -2.8 + epsilon);
assert(weights.getPartialDerivative(2, 1) > -8.4 - epsilon &&
weights.getPartialDerivative(2, 1) < -8.4 + epsilon);
assert(weights.getBiasPartialDerivative(0) < 0.65 + epsilon &&
weights.getBiasPartialDerivative(0) > 0.65 - epsilon);
assert(weights.getBiasPartialDerivative(1) < -2.8 + epsilon &&
weights.getBiasPartialDerivative(1) > -2.8 - epsilon);
printPass("TestWeightMatrix_Backward()");
}
//------------------ANN construction------------------------------------------
void ANN (int N,float In, float * w_ji, float * w_kj, float b, float * y_pj,float & y_pk) {
float x_pi;
input_layer(In,x_pi);
hidden_layer(N,x_pi, w_ji, y_pj);
output_layer(N,y_pj,w_kj,b,y_pk);
}
/******************************************************************************
* DXF output function.
*/
int output_dxf12_writer(FILE* dxf_file, gchar* name,
int llx, int lly, int urx, int ury,
at_output_opts_type * opts,
spline_list_array_type shape,
at_msg_func msg_func,
gpointer msg_data,
gpointer user_data)
{
OUT_LINE (" 0");
OUT_LINE ("SECTION");
OUT_LINE (" 2");
OUT_LINE ("HEADER");
OUT_LINE (" 9");
OUT_LINE ("$ACADVER");
OUT_LINE (" 1");
OUT_LINE ("AC1009");
OUT_LINE (" 9");
OUT_LINE ("$EXTMIN");
OUT_LINE (" 10");
OUT1 (" %f\n", (double)llx);
OUT_LINE (" 20");
OUT1 (" %f\n", (double)lly);
OUT_LINE (" 30");
OUT_LINE (" 0.000000");
OUT_LINE (" 9");
OUT_LINE ("$EXTMAX");
OUT_LINE (" 10");
OUT1 (" %f\n", (double)urx);
OUT_LINE (" 20");
OUT1 (" %f\n", (double)ury);
OUT_LINE (" 30");
OUT_LINE (" 0.000000");
OUT_LINE (" 0");
OUT_LINE ("ENDSEC");
output_layer(dxf_file, shape);
OUT_LINE (" 0");
OUT_LINE ("SECTION");
OUT_LINE (" 2");
OUT_LINE ("ENTITIES");
out_splines(dxf_file, shape);
OUT_LINE (" 0");
OUT_LINE ("ENDSEC");
OUT_LINE (" 0");
OUT_LINE ("EOF");
return 0;
}
void TestHiddenLayer_Backward() {
double epsilon = 1e-3;
int n_outputs = 2;
int n_inputs = 3;
HiddenLayer hidden_layer(n_inputs);
OutputLayer output_layer(n_outputs);
std::vector<double> hidden_values;
hidden_values.push_back(-2.0);
hidden_values.push_back(1.0);
hidden_values.push_back(3.0);
WeightMatrix weights(hidden_layer, output_layer);
weights.set(0, 0, 0.5);
weights.set(1, 0, -2.0);
weights.set(2, 0, 1.5);
weights.set(0, 1, 1.0);
weights.set(1, 1, 0.7);
weights.set(2, 1, -1.0);
weights.setBias(0, 0.8);
weights.setBias(1, -0.3);
hidden_layer.receiveInput(hidden_values);
std::vector<double> transition = weights.fire(hidden_layer);
output_layer.receiveInput(transition);
assert(output_layer.getInput(0) == 3.3);
assert(output_layer.getInput(1) == -2.6);
// backpropagation step
std::vector<double> actual_outputs;
actual_outputs.push_back(1.0);
actual_outputs.push_back(1.0);
output_layer.computeGradient(actual_outputs);
weights.computeGradient(hidden_layer, output_layer);
hidden_layer.computeGradient(weights, output_layer);
assert(hidden_layer.getPartialDerivative(0) < 0.0 + epsilon &&
hidden_layer.getPartialDerivative(0) > 0.0 - epsilon);
assert(hidden_layer.getPartialDerivative(1) < -3.56 + epsilon &&
hidden_layer.getPartialDerivative(1) > -3.56 - epsilon);
assert(hidden_layer.getPartialDerivative(2) < 3.525 + epsilon &&
hidden_layer.getPartialDerivative(2) > 3.525 - epsilon);
printPass("TestHiddenLayer_Backward()");
}
void TestWeightMatrix_Forward() {
int n_outputs = 2;
InputLayer input_layer(3);
OutputLayer output_layer(n_outputs);
WeightMatrix weights(input_layer, output_layer);
weights.set(0, 0, 0.5);
weights.set(1, 0, -2.0);
weights.set(2, 0, 1.5);
weights.set(0, 1, 1.0);
weights.set(1, 1, 0.7);
weights.set(2, 1, -1.0);
weights.setBias(0, 0.8);
weights.setBias(1, -0.3);
std::vector<double> inputs;
inputs.push_back(-2.0);
inputs.push_back(1.0);
inputs.push_back(3.0);
input_layer.receiveInput(inputs);
std::vector<double> transition = weights.fire(input_layer);
assert(transition.size() == 2);
assert(transition[0] == 2.3);
assert(transition[1] == -4.6);
output_layer.receiveInput(transition);
assert(output_layer.getInput(0) == 2.3);
assert(output_layer.getInput(1) == -4.6);
assert(output_layer.getOutput(0) == 2.3);
assert(output_layer.getOutput(1) == -4.6);
printPass("TestWeightMatrix_Forward()");
}