DeepAI AI Chat
Log In Sign Up

Neural-Symbolic Integration: A Compositional Perspective

10/22/2020
by   Efthymia Tsamoura, et al.
0

Despite significant progress in the development of neural-symbolic frameworks, the question of how to integrate a neural and a symbolic system in a compositional manner remains open. Our work seeks to fill this gap by treating these two systems as black boxes to be integrated as modules into a single architecture, without making assumptions on their internal structure and semantics. Instead, we expect only that each module exposes certain methods for accessing the functions that the module implements: the symbolic module exposes a deduction method for computing the function's output on a given input, and an abduction method for computing the function's inputs for a given output; the neural module exposes a deduction method for computing the function's output on a given input, and an induction method for updating the function given input-output training instances. We are, then, able to show that a symbolic module – with any choice for syntax and semantics, as long as the deduction and abduction methods are exposed – can be cleanly integrated with a neural module, and facilitate the latter's efficient training, achieving empirical performance that exceeds that of previous work.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/06/2016

Neuro-Symbolic Program Synthesis

Recent years have seen the proposal of a number of neural architectures ...
08/15/2020

Compositional Generalization via Neural-Symbolic Stack Machines

Despite achieving tremendous success, existing deep learning models have...
02/05/2016

Harmonic Grammar in a DisCo Model of Meaning

The model of cognition developed in (Smolensky and Legendre, 2006) seeks...
04/04/2021

A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference Resolution

Event coreference resolution is an important research problem with many ...
10/11/2017

The Refinement Calculus of Reactive Systems

The Refinement Calculus of Reactive Systems (RCRS) is a compositional fo...
03/06/2023

Symbolic Synthesis of Neural Networks

Neural networks adapt very well to distributed and continuous representa...
10/08/2019

Meta Module Network for Compositional Visual Reasoning

There are two main lines of research on visual reasoning: neural module ...