AILGLOJun 23, 2020

Logical Neural Networks

arXiv:2006.13155v1201 citations
Originality Highly original
AI Analysis

This work addresses the problem of combining learning and reasoning for AI researchers, offering a novel framework that bridges neural and symbolic approaches.

The authors tackled the challenge of integrating neural networks' learning capabilities with symbolic logic's interpretability and reasoning, resulting in a differentiable model that supports logical inference and is resilient to inconsistent and incomplete knowledge.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes