Towards heuristic algorithmic memory
dc.citation.epage | 387 | en_US |
dc.citation.spage | 382 | en_US |
dc.citation.volumeNumber | 6830 | en_US |
dc.contributor.author | Özkural, Eray | en_US |
dc.coverage.spatial | Mountain View, CA, USA | en_US |
dc.date.accessioned | 2016-02-08T12:19:00Z | |
dc.date.available | 2016-02-08T12:19:00Z | |
dc.date.issued | 2011 | en_US |
dc.department | Department of Computer Engineering | en_US |
dc.description | Date of Conference: August 3-6, 2011 | en_US |
dc.description | Conference name: 4th International Conference, AGI 2011 | en_US |
dc.description.abstract | We propose a long-term memory design for artificial general intelligence based on Solomonoff's incremental machine learning methods. We introduce four synergistic update algorithms that use a Stochastic Context-Free Grammar as a guiding probability distribution of programs. The update algorithms accomplish adjusting production probabilities, re-using previous solutions, learning programming idioms and discovery of frequent subprograms. A controlled experiment with a long training sequence shows that our incremental learning approach is effective. © 2011 Springer-Verlag Berlin Heidelberg. | en_US |
dc.description.provenance | Made available in DSpace on 2016-02-08T12:19:00Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 2011 | en |
dc.identifier.doi | 10.1007/978-3-642-22887-2_47 | en_US |
dc.identifier.doi | 10.1007/978-3-642-22887-2 | en_US |
dc.identifier.issn | 0302-9743 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/28377 | en_US |
dc.language.iso | English | en_US |
dc.publisher | Springer, Berlin, Heidelberg | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1007/978-3-642-22887-2_47 | en_US |
dc.relation.isversionof | https://doi.org/10.1007/978-3-642-22887-2 | en_US |
dc.source.title | Artificial General Intelligence | en_US |
dc.subject | Controlled experiment | en_US |
dc.subject | General Intelligence | en_US |
dc.subject | Incremental learning | en_US |
dc.subject | Learning programming | en_US |
dc.subject | Long term memory | en_US |
dc.subject | Machine learning methods | en_US |
dc.subject | Stochastic context free grammar | en_US |
dc.subject | Subprograms | en_US |
dc.subject | Training sequences | en_US |
dc.subject | Algorithms | en_US |
dc.subject | Context free grammars | en_US |
dc.subject | Learning systems | en_US |
dc.subject | Probability distributions | en_US |
dc.subject | Heuristic methods | en_US |
dc.title | Towards heuristic algorithmic memory | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Towards heuristic algorithmic memory.pdf
- Size:
- 138.86 KB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version