We present a hybrid system for managing both symbolic and subsymbolic knowledge in a uniform way. Our aim is to solve problems where some gap in formal theories occurs which stops us from getting a fully symbolical solution. The idea is to use neural modules to functionally connect pieces of symbolical knowledge, such as mathematical formulas and deductive rules. The whole system is trained through a backpropagation learning algorithm where all (symbolic or subsymbolic) free parameters are updated piping back the error through each component of the system. The structure of this system is very general, possibly varying over time, possibly managing fuzzy variables and decision trees. We use as a test-bed the problem of sorting a file, where suitable suggestions on next sorting moves are supplied by the network also on the basis of hints provided by some conventional sorters. A comprehensive discussion of system performance is provided in order to understand behaviors and capabilities of the proposed hybrid system.

Apolloni, B., Zoppis, I. (1999). Sub-symbolically managing pieces of symbolical functions for sorting. IEEE TRANSACTIONS ON NEURAL NETWORKS, 10(5), 1099-1122 [10.1109/72.788650].

Sub-symbolically managing pieces of symbolical functions for sorting

ZOPPIS, ITALO FRANCESCO
1999

Abstract

We present a hybrid system for managing both symbolic and subsymbolic knowledge in a uniform way. Our aim is to solve problems where some gap in formal theories occurs which stops us from getting a fully symbolical solution. The idea is to use neural modules to functionally connect pieces of symbolical knowledge, such as mathematical formulas and deductive rules. The whole system is trained through a backpropagation learning algorithm where all (symbolic or subsymbolic) free parameters are updated piping back the error through each component of the system. The structure of this system is very general, possibly varying over time, possibly managing fuzzy variables and decision trees. We use as a test-bed the problem of sorting a file, where suitable suggestions on next sorting moves are supplied by the network also on the basis of hints provided by some conventional sorters. A comprehensive discussion of system performance is provided in order to understand behaviors and capabilities of the proposed hybrid system.
Articolo in rivista - Articolo scientifico
backpropagation, decision trees, recurrent neural nets, sorting, symbol manipulation
English
1999
10
5
1099
1122
none
Apolloni, B., Zoppis, I. (1999). Sub-symbolically managing pieces of symbolical functions for sorting. IEEE TRANSACTIONS ON NEURAL NETWORKS, 10(5), 1099-1122 [10.1109/72.788650].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/10281/27996
Citazioni
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 5
Social impact