- Titel
- Neural-Symbolic Integration
- Zitierfähige Url:
- https://nbn-resolving.org/urn:nbn:de:bsz:14-qucosa-25468
- Übersetzter Titel (DE)
- Neuro-Symbolische Integration
- Datum der Einreichung
- 07.08.2009
- Datum der Verteidigung
- 05.10.2009
- Abstract (EN)
- In this thesis, we discuss different techniques to bridge the gap between two different approaches to artificial intelligence: the symbolic and the connectionist paradigm. Both approaches have quite contrasting advantages and disadvantages. Research in the area of neural-symbolic integration aims at bridging the gap between them. Starting from a human readable logic program, we construct connectionist systems, which behave equivalently. Afterwards, those systems can be trained, and later the refined knowledge be extracted.
- Freie Schlagwörter (DE)
- Neuro-Symbolische Integration, Neuronale Netze, Logische Programme, Regelextraktion, Regeleinbettung, Regelverfeinerung
- Freie Schlagwörter (EN)
- Neural-Symbolic Integration, Neural Networks, Logic Programs, Rule Extraction, Rule Embedding, Rule Refinement
- Klassifikation (DDC)
- 004
- Klassifikation (RVK)
- ST 301
- GutachterIn
- Prof. Dr. rer. nat. habil Steffen Hölldobler
- Prof. Dr. rer. nat. habil Barbara Hammer
- BetreuerIn
- Prof. Dr. rer. nat. habil Steffen Hölldobler
- Den akademischen Grad verleihende / prüfende Institution
- Technische Universität Dresden, Dresden
- URN Qucosa
- urn:nbn:de:bsz:14-qucosa-25468
- Veröffentlichungsdatum Qucosa
- 15.12.2009
- Dokumenttyp
- Dissertation
- Sprache des Dokumentes
- Englisch
- Lizenz / Rechtehinweis
