A Computational Perspective on Neural-Symbolic Integration

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F24%3A00375262" target="_blank" >RIV/68407700:21230/24:00375262 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.3233/NAI-240672" target="_blank" >https://doi.org/10.3233/NAI-240672</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.3233/NAI-240672" target="_blank" >10.3233/NAI-240672</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Computational Perspective on Neural-Symbolic Integration

Popis výsledku v původním jazyce

Neural-Symbolic Integration (NSI) aims to marry the principles of symbolic AI techniques, such as logical reasoning, with the learning capabilities of neural networks. In recent years, many systems have been proposed to address this integration in a seemingly {{efficient}} manner. However, from the computational perspective, this is in principle impossible to do. Specifically, some of the core symbolic problems are provably hard, hence a general NSI system necessarily needs to adopt this computational complexity, too. Many NSI methods try to circumvent this downside by inconspicuously dropping parts of the symbolic capabilities while mapping the problems into static tensor representations in exchange for efficient deep learning acceleration. In this paper, we argue that the aim for a general NSI system, {properly} covering both the neural and symbolic paradigms, has important computational implications on the learning representations, the structure of the resulting computation graphs, and the underlying hardware and software stacks. Particularly, we explain how the currently prominent, tensor-based deep learning with static computation graphs is conceptually insufficient as a foundation for such general NSI, which we discuss in a wider context of established (statistical) relational and structured deep learning methods. Finally, we delve into the underlying hardware acceleration aspects and outline some promising computational directions toward fully expressive and efficient NSI.

Název v anglickém jazyce

A Computational Perspective on Neural-Symbolic Integration

Popis výsledku anglicky

Neural-Symbolic Integration (NSI) aims to marry the principles of symbolic AI techniques, such as logical reasoning, with the learning capabilities of neural networks. In recent years, many systems have been proposed to address this integration in a seemingly {{efficient}} manner. However, from the computational perspective, this is in principle impossible to do. Specifically, some of the core symbolic problems are provably hard, hence a general NSI system necessarily needs to adopt this computational complexity, too. Many NSI methods try to circumvent this downside by inconspicuously dropping parts of the symbolic capabilities while mapping the problems into static tensor representations in exchange for efficient deep learning acceleration. In this paper, we argue that the aim for a general NSI system, {properly} covering both the neural and symbolic paradigms, has important computational implications on the learning representations, the structure of the resulting computation graphs, and the underlying hardware and software stacks. Particularly, we explain how the currently prominent, tensor-based deep learning with static computation graphs is conceptually insufficient as a foundation for such general NSI, which we discuss in a wider context of established (statistical) relational and structured deep learning methods. Finally, we delve into the underlying hardware acceleration aspects and outline some promising computational directions toward fully expressive and efficient NSI.

Druh

J_ost - Ostatní články v recenzovaných periodicích

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA24-11664S" target="_blank" >GA24-11664S: Relační posilované učení pro akceleraci vědy</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Neurosymbolic Artificial Intelligence

ISSN

2949-8732

e-ISSN

2949-8732

Svazek periodika

1

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

12

Strana od-do

1-12

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—