Logical Neural Networks
read the original abstract
We propose a novel framework seamlessly providing key properties of both neural nets (learning) and symbolic logic (knowledge and reasoning). Every neuron has a meaning as a component of a formula in a weighted real-valued logic, yielding a highly intepretable disentangled representation. Inference is omnidirectional rather than focused on predefined target variables, and corresponds to logical reasoning, including classical first-order logic theorem proving as a special case. The model is end-to-end differentiable, and learning minimizes a novel loss function capturing logical contradiction, yielding resilience to inconsistent knowledge. It also enables the open-world assumption by maintaining bounds on truth values which can have probabilistic semantics, yielding resilience to incomplete knowledge.
This paper has not been read by Pith yet.
Forward citations
Cited by 12 Pith papers
-
Explicit Fuzzy Logic in the Feed-Forward Layer: Self-Forgetting Quantifiers Discover Legible Grammatical-Licensing Detectors
A parameter-neutral fuzzy-logic FFN augmented with self-forgetting quantifiers produces legible grammatical-licensing detectors while matching baseline perplexity on OpenWebText.
-
First-Order Temporal Logic Tensor Networks
FOT-LTN extends Logic Tensor Networks by integrating first-order linear temporal logic syntax with fuzzy differentiable semantics, supporting temporal operators and quantifiers, and shows improved performance over neu...
-
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
Outcome-fair credit models often exhibit hidden procedural bias through inconsistent reasoning across groups, which the CEC framework mitigates by enforcing consistent feature attributions via counterfactuals.
-
AttackPathGNN: Cross-function vulnerability detection in smart contracts using state interference graphs and conjunction pooling
AttackPathGNN introduces a State Interference Graph and conjunction pooling inside a GNN to detect cross-function vulnerabilities in Solidity contracts, reporting 92.3% F1 on SmartBugs Wild.
-
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
A conditional invariance framework defines explanation fairness as explanations being statistically independent of protected attributes given task-relevant features, unifying existing metrics and enabling procedural b...
-
Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA
Temporal reasoning is not the core bottleneck for LLMs on time-based QA; the real issue is unstructured text-to-event mapping, addressed by a neuro-symbolic system with PIS that reaches 100% accuracy on benchmarks whe...
-
Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants
A symbolic protocol operationalizes Peirce's tripartite reasoning for LLMs using five algebraic invariants including a Weakest Link bound to enforce logical consistency and prevent weak premises from supporting strong...
-
THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular Architecture
A modular neural architecture learns complete Kleene three-valued logic from task data and exhibits uncertainty-preserving propagation plus superior 500-step generalization under Gumbel-softmax training where flat MLP...
-
Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration
LoH adds a learnable choice operator to propositional logic, compiles formulas to differentiable graphs via fuzzy logic, subsumes prior NeSy models, and supports discretization to Boolean functions via the Gödel trick.
-
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.
-
Overmind NSA: A Unified Neuro-Symbolic Computing Architecture with Approximate Nonlinear Activations and Preemptive Memory Bypass
Overmind is a neuro-symbolic architecture that uses adjustable Padé approximations and memory bypass to deliver 8.1 TOPS/W efficiency and 410 GOPS throughput on mixed workloads with minimal accuracy loss.
-
Auto-Relational Reasoning
A system using auto-relational reasoning solves IQ test problems at 98.03% rate without any prior knowledge, reaching top 1% human performance.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.