Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases

Abstract

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognised as one of the key challenges of modern AI. Recent years have seen large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse and mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognised until now. Finally, our design patterns extend and refine Kautz' earlier attempt at categorising neuro-symbolic architectures.

Natlog: a Lightweight Logic Programming Language with a Neuro-symbolic Touch

“…Running the query: n=natlog(text=prog) for answer in n.solve("perm (a (b (c ()))) P? "): print(answer [2])…”

“…we obtain a stream of answers yield by our interpreter pretending to be a Python generator: Note that in this proof-of-concept implementation list constructors are simply nested tuples of length 2 and components of the answer tuples yield by the interpreter can be accessed with the usual array index notation as in answer [2], selecting the argument P of the tuple (perm _ P).…”

“…In [7] a large number of neuro-symbolic systems are surveyed, along multiple features, among which we mention the focus on the expressiveness of the logic (ranging from propositional to first order predicate logic) and probabilistic or deterministic nature. An ontology of design patterns for neuro-symbolic systems is explored in [2], to which our neural ground fact database indexer would be a possibly new addition.…”

“…With renewed interest in neuro-symbolic AI [8,10,7,2], integration of logic programming languages into deep-learning ecosystems is becoming of paramount importance. Today's deep-learning frameworks like tensorflow 1 and torch 2 and machine-learning frameworks like scikit-learn 3 [13] are all as available as Python packages.…”

“…With renewed interest in neuro-symbolic AI [8,10,7,2], integration of logic programming languages into deep-learning ecosystems is becoming of paramount importance. Today's deep-learning frameworks like tensorflow 1 and torch 2 and machine-learning frameworks like scikit-learn 3 [13] are all as available as Python packages. The need to interoperate with them suggests embedding in the same ecosystem an easy to use, syntactically and semantically lightweight logic programming language, that allows datascientists with limited exposure to logic programming to build neuro-symbolic systems with enhanced reasoning abilities.…”