Real-Logic-style knowledge-base satisfaction loss – Phase 1 Mission 1 of campaign_exai_dl_library_neuro_symbolic. More...

#include "pulsatrix/aggregator_module.hpp"
#include "pulsatrix/device_backend.hpp"
#include "pulsatrix/tensor.hpp"

Include dependency graph for satisfaction_loss.hpp:

This graph shows which files directly or indirectly include this file:

Classes
class	pulsatrix::SatisfactionLoss
	`loss = 1 - agg_p(truth_values)` – the standard LTN "Real Logic" training objective (research_2026_neuro_symbolic_ai.md §1/§2): maximizing a knowledge base's aggregated satisfaction via ordinary gradient descent is the same as minimizing this loss. More...

Detailed Description

Real-Logic-style knowledge-base satisfaction loss – Phase 1 Mission 1 of campaign_exai_dl_library_neuro_symbolic.

Classes