Abstract
Neuro-Symbolic Integration is an interdisciplinary area that endeavours to unify neural networks and symbolic logic. The goal is to create a system that combines the advantages of neural networks (adaptive behaviour, robustness, tolerance of noise and probability) and symbolic logic (validity of computations, generality, higher-order reasoning). Several different approaches have been proposed in the past. However, the existing neuro-symbolic networks provide only a limited coverage of the techniques used in computational logic. In this paper, we outline the areas of neuro-symbolism where computational logic has been implemented so far, and analyse the problematic areas. We show why certain concepts cannot be implemented using the existing neuro-symbolic networks, and propose four main improvements needed to build neuro-symbolic networks of the future.
Original language | English |
---|---|
Title of host publication | IJCCI 2009: Proceedings of the International Joint Conference on Computational Intelligence |
Editors | A Dourado, A Rosa, K Madani |
Place of Publication | Setubal |
Publisher | Institute for Systems and Technologies of Information, Control and Communication |
Pages | 502-507 |
Number of pages | 6 |
ISBN (Print) | 9789896740146 |
Publication status | Published - 2009 |
Event | 1st International Joint Conference on Computational Intelligence - Funchal, Portugal Duration: 5 Oct 2009 → 7 Oct 2009 |
Conference
Conference | 1st International Joint Conference on Computational Intelligence |
---|---|
Abbreviated title | IJCCI 2009 |
Country/Territory | Portugal |
City | Funchal |
Period | 5/10/09 → 7/10/09 |
Keywords
- Computational logic in neural networks
- Neuro-symbolic networks
- Connectionism
- Hybrid networks
- NEURAL-NETWORKS
- COMPUTABILITY
- UNIVERSALITY
- NETS