Deep Learning with Relational Logic Representations

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00333120" target="_blank" >RIV/68407700:21230/19:00333120 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.ijcai.org/proceedings/2019/920" target="_blank" >https://www.ijcai.org/proceedings/2019/920</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.24963/ijcai.2019/920" target="_blank" >10.24963/ijcai.2019/920</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning with Relational Logic Representations

Popis výsledku v původním jazyce

Despite their significant success, all the existing deep neural architectures based on static computational graphs processing fixed tensor representations necessarily face fundamental limitations when presented with dynamically sized and structured data. Examples of these are sparse multi-relational structures present everywhere from biological networks and complex knowledge hyper-graphs to logical theories. Likewise, given the cryptic nature of generalization and representation learning in neural networks, potential integration with the sheer amounts of existing symbolic abstractions present in human knowledge remains highly problematic. Here, we argue that these abilities, naturally present in symbolic approaches based on the expressive power of relational logic, are necessary to be adopted for further progress of neural networks, and present a well founded learning framework for integration of deep and symbolic approaches based on the lifted modelling paradigm.

Název v anglickém jazyce

Deep Learning with Relational Logic Representations

Popis výsledku anglicky

Despite their significant success, all the existing deep neural architectures based on static computational graphs processing fixed tensor representations necessarily face fundamental limitations when presented with dynamically sized and structured data. Examples of these are sparse multi-relational structures present everywhere from biological networks and complex knowledge hyper-graphs to logical theories. Likewise, given the cryptic nature of generalization and representation learning in neural networks, potential integration with the sheer amounts of existing symbolic abstractions present in human knowledge remains highly problematic. Here, we argue that these abilities, naturally present in symbolic approaches based on the expressive power of relational logic, are necessary to be adopted for further progress of neural networks, and present a well founded learning framework for integration of deep and symbolic approaches based on the lifted modelling paradigm.

Druh

D - Stať ve sborníku

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/GA17-26999S" target="_blank" >GA17-26999S: Hluboké relační učení</a><br>

Návaznosti

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

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

ISBN

978-0-9992411-4-1

ISSN

—

e-ISSN

1045-0823

Počet stran výsledku

2

Strana od-do

6462-6463

Název nakladatele

International Joint Conferences on Artificial Intelligence Organization

Místo vydání

—

Místo konání akce

Macau

Datum konání akce

10. 8. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—