fixed_topology_xor_network.hpp File Reference

A small, fixed-topology (2 input -> 2 hidden -> 1 output, both layers sigmoid) MLP whose weights are a flat parameter vector, plus a plain analytic fitness function scoring it against the four XOR patterns – the "fixed-topology network" and "plain analytic fitness function" this campaign's Evolution Strategies mission needs, deliberately using the same XOR benchmark and the same fitness convention (4.0 minus sum of squared error) as Mission 2's NEAT proof, for a direct same-problem cross-check between the two techniques. More...

#include <array>
#include <cmath>
#include <stdexcept>
#include <vector>

Include dependency graph for fixed_topology_xor_network.hpp:

Go to the source code of this file.

Namespaces
namespace	pulsatrix
namespace	pulsatrix::detail

Functions
double	pulsatrix::detail::Sigmoid (double x)
double	pulsatrix::FixedTopologyXORForward (const std::vector< double > &theta, const std::array< double, 2 > &inputs)
	Forward pass: theta layout is [w1_00, w1_01, b1_0, w1_10, w1_11, b1_1, w2_0, w2_1, b2] – h_j = sigmoid(w1_j0*x0 + w1_j1*x1 + b1_j) for j in {0,1}, y = sigmoid(w2_0*h0 + w2_1*h1 + b2).
double	pulsatrix::FixedTopologyXORFitness (const std::vector< double > &theta)
	Scores theta against all four XOR patterns as 4.0 minus the sum of squared errors – identical convention to XORFitness (neat_xor_fitness.hpp), so an all-zero theta scores exactly 3.0 (every pattern outputs sigmoid(0)=0.5), the same fixed point NEAT's own fresh, all-zero-weight genome scores.

Variables
constexpr size_t	pulsatrix::kFixedTopologyXORNumParams = 9
	Total flat-parameter count: 2*2 (input->hidden weights) + 2 (hidden biases) + 2 (hidden->output weights) + 1 (output bias) = 9.

Detailed Description

A small, fixed-topology (2 input -> 2 hidden -> 1 output, both layers sigmoid) MLP whose weights are a flat parameter vector, plus a plain analytic fitness function scoring it against the four XOR patterns – the "fixed-topology network" and "plain analytic fitness function" this campaign's Evolution Strategies mission needs, deliberately using the same XOR benchmark and the same fitness convention (4.0 minus sum of squared error) as Mission 2's NEAT proof, for a direct same-problem cross-check between the two techniques.

Note

Not a Module – ES needs no gradient/backward pass at all (it is itself a gradient-free, black-box optimizer), so there is nothing here for ComputationGraph/Autograd/LRP to attach to; this mirrors NEAT's own phenotype's already-logged Risk Register scope cut for the same underlying reason.