Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning
| dc.contributor.author | Juozapaitis, Jeffrey James | |
| dc.creator | Juozapaitis, Jeffrey James | en_US |
| dc.date.accessioned | 2013-03-08T21:12:17Z | |
| dc.date.available | 2013-03-08T21:12:17Z | |
| dc.date.issued | 2012 | |
| dc.identifier.citation | Juozapaitis, Jeffrey James. (2012). Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning (Bachelor's thesis, University of Arizona, Tucson, USA). | |
| dc.identifier.uri | http://hdl.handle.net/10150/271607 | |
| dc.description.abstract | In this paper, we learn a simple conceptual card game as learned by David Stracuzzi's Cumulus algorithm. We then posit a (sadly unimplemented) scheme to transfer the neural net created by it to a similar game with small modifications, hopefully cutting down the learning time. We then analyze the flaws with the transfer scheme and posit other schemes that may produce better results. | |
| dc.language.iso | en | en_US |
| dc.publisher | The University of Arizona. | en_US |
| dc.rights | Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author. | en_US |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | |
| dc.title | Exploring Supervised Many Layered Learning as a Precursor to Transfer Learning | en_US |
| dc.type | text | en_US |
| dc.type | Electronic Thesis | en_US |
| thesis.degree.grantor | University of Arizona | en_US |
| thesis.degree.level | bachelors | en_US |
| thesis.degree.discipline | Honors College | en_US |
| thesis.degree.discipline | Computer Science | en_US |
| thesis.degree.name | B.S. | en_US |
| dc.description.admin-note | Removed permission form from PDF and replaced file June 2023 | |
| refterms.dateFOA | 2018-04-25T22:42:59Z | |
| html.description.abstract | In this paper, we learn a simple conceptual card game as learned by David Stracuzzi's Cumulus algorithm. We then posit a (sadly unimplemented) scheme to transfer the neural net created by it to a similar game with small modifications, hopefully cutting down the learning time. We then analyze the flaws with the transfer scheme and posit other schemes that may produce better results. |
