Wires a real neural predicate (LinearModule + sigmoid, reusing Phase 1 Mission 2's ToyKnowledgeBase pattern) into the weighted Datalog engine as one base fact's weight, on a small diamond-graph transitive-closure toy program (Mission 0/1's own ancestor shape). Computes the gradient of a derived query fact's weight w.r.t. the neural predicate's output (via forward-mode AD over the provenance semiring, see datalog_dual_semiring.hpp) and, transitively, the predicate's LinearModule parameters (via that module's own real backward(), mirroring ToyKnowledgeBase's hand-chained-Module::backward() precedent). Phase 3 Mission 2 of campaign_exai_dl_library_neuro_symbolic (Neural-Predicate Integration). More...

#include "pulsatrix/datalog_dual_semiring.hpp"
#include "pulsatrix/datalog_lrp.hpp"
#include "pulsatrix/datalog_rule.hpp"
#include "pulsatrix/datalog_semiring.hpp"
#include "pulsatrix/datalog_weighted_fact_database.hpp"
#include "pulsatrix/linear_module.hpp"
#include "pulsatrix/lrp_rule_config.hpp"
#include "pulsatrix/tensor.hpp"

Include dependency graph for neuro_symbolic_datalog_bridge.hpp:

Go to the source code of this file.

Classes
struct	pulsatrix::datalog::NeuralPredicateQueryResult
	The two numbers a forward pass through the bridge produces: the derived query fact's real-valued weight, and its exact partial derivative w.r.t. the neural predicate's (sigmoid-squashed) output – both computed in the same `DualSemiring<double>` evaluation pass (see datalog_dual_semiring.hpp). More...

struct	pulsatrix::datalog::NeuralPredicateRelevanceResult
	The result of one `NeuralPredicateDatalogBridge::propagate_relevance()` call – Phase 3 Mission 3's own deliverable (LRP for the Datalog/provenance-semiring circuit), extended end-to-end through the neural predicate's own `Module` chain. More...

class	pulsatrix::datalog::NeuralPredicateDatalogBridge
	Bridges one neural-predicate-weighted base fact into the real-valued weighted Datalog engine. More...

Namespaces
namespace	pulsatrix

namespace	pulsatrix::datalog

Detailed Description

Wires a real neural predicate (LinearModule + sigmoid, reusing Phase 1 Mission 2's ToyKnowledgeBase pattern) into the weighted Datalog engine as one base fact's weight, on a small diamond-graph transitive-closure toy program (Mission 0/1's own ancestor shape). Computes the gradient of a derived query fact's weight w.r.t. the neural predicate's output (via forward-mode AD over the provenance semiring, see datalog_dual_semiring.hpp) and, transitively, the predicate's LinearModule parameters (via that module's own real backward(), mirroring ToyKnowledgeBase's hand-chained-Module::backward() precedent). Phase 3 Mission 2 of campaign_exai_dl_library_neuro_symbolic (Neural-Predicate Integration).

Classes

Namespaces

Detailed Description