Integrating logic reasoning and deep learning from sensory data is a key challenge to develop artificial agents able to operate in complex environments. Whereas deep learning can operate at a large scale thanks to recent hardware advancements (GPUs) as well as other important technical advancements like Stochastic Gradient Descent, logic inference can not be executed over large reasoning tasks, as it requires to consider a combinatorial number of possible assignments. Relational Neural Machines (RNMs) have been recently introduced in order to co-train a deep learning machine and a first-order probabilistic logic reasoner in a fully integrated way. In this context, it is crucial to avoid the logic inference to become a bottleneck, preventing the application of the methodology to large scale learning tasks. This paper proposes and compares different inference schemata for Relational Neural Machines together with some preliminary results to show the effectiveness of the proposed methodologies.

Marra, G., Diligenti, M., Faggi, L., Giannini, F., Gori, M., Maggini, M. (2020). Inference in relational neural machines. In CEUR Workshop Proceedings (pp.71-74). CEUR-WS.

Inference in relational neural machines

Marra, G.;Diligenti, M.;Giannini, F.;Gori, M.;Maggini, M.
2020-01-01

Abstract

Integrating logic reasoning and deep learning from sensory data is a key challenge to develop artificial agents able to operate in complex environments. Whereas deep learning can operate at a large scale thanks to recent hardware advancements (GPUs) as well as other important technical advancements like Stochastic Gradient Descent, logic inference can not be executed over large reasoning tasks, as it requires to consider a combinatorial number of possible assignments. Relational Neural Machines (RNMs) have been recently introduced in order to co-train a deep learning machine and a first-order probabilistic logic reasoner in a fully integrated way. In this context, it is crucial to avoid the logic inference to become a bottleneck, preventing the application of the methodology to large scale learning tasks. This paper proposes and compares different inference schemata for Relational Neural Machines together with some preliminary results to show the effectiveness of the proposed methodologies.
2020
Marra, G., Diligenti, M., Faggi, L., Giannini, F., Gori, M., Maggini, M. (2020). Inference in relational neural machines. In CEUR Workshop Proceedings (pp.71-74). CEUR-WS.
File in questo prodotto:
File Dimensione Formato  
marra.pdf

accesso aperto

Tipologia: PDF editoriale
Licenza: Creative commons
Dimensione 448.63 kB
Formato Adobe PDF
448.63 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/1122218