A dynamic binding mechanism for retrieving and unifying complex predicate-logic knowledge

Authors:
Gadi Pinkas;Priscila Lima;Shimon Cohen
Affiliations:
Center for Academic Studies, Israel;Federal Rural University of Rio de Janeiro, Brazil;Center for Academic Studies, Israel
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 10
Cited 0

Connectionism and cognitive architecture: a critical analysis

Connections and symbols
Symmetric neural networks and propositional logic satisfiability

Neural Computation
Reasoning, nonmonotonicity and learning in connectionist networks that capture propositional knowledge

Artificial Intelligence
CHCL - A Connectionist Infernce System

Proceedings of the International Workshop on Parallelization in Inference Systems
Unification as constraint satisfaction in structured connectionist networks

Neural Computation
Connectionist model generation: A first-order approach

Neurocomputing
A (somewhat) new solution to the variable binding problem

Neural Computation
Neural-Symbolic Cognitive Reasoning

Neural-Symbolic Cognitive Reasoning
A structured connectionist unification algorithm

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1
Holographic reduced representations

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show how to encode, retrieve and process complex structures equivalent to First-Order Logic (FOL) formulae, with Artificial Neural Networks (ANNs) designed for energy-minimization. The solution constitutes a binding mechanism that uses a neural Working Memory (WM) and a long-term synaptic memory (LTM) that can store both procedural and declarative FOL-like Knowledge-Base (KB). Complex structures stored in LTM are retrieved into the WM only upon need, where they are further processed. The power of our binding mechanism is demonstrated on unification problems: as neurons are dynamically allocated from a pool, most generally unified structures emerge at equilibrium. The network's size is O(n·k), where n is the size of the retrieved FOL structures and k is the size of the KB. The mechanism is fault-tolerant, as no fatal failures occur when random units fail. The paradigm can be used in a variety of applications, such as language processing, reasoning and planning.