Please use this identifier to cite or link to this item:
https://scholarbank.nus.edu.sg/handle/10635/170591
DC Field | Value | |
---|---|---|
dc.title | AN IMPROVED UNSUPERVISED TRAINING ALGORITHM FOR NEOCOGNITRON | |
dc.contributor.author | CHOW KWOK WAH | |
dc.date.accessioned | 2020-06-22T05:24:54Z | |
dc.date.available | 2020-06-22T05:24:54Z | |
dc.date.issued | 1995 | |
dc.identifier.citation | CHOW KWOK WAH (1995). AN IMPROVED UNSUPERVISED TRAINING ALGORITHM FOR NEOCOGNITRON. ScholarBank@NUS Repository. | |
dc.identifier.uri | https://scholarbank.nus.edu.sg/handle/10635/170591 | |
dc.description.abstract | Based on computer simulations, we have investigated the unsupervised training algorithm of neocognitron. We observed that extended and strong features such as line segments are extracted in the intermediate stages, due to a positive feedback effect in the training algorithm. We then propose a refined training algorithm that discourages the extraction of these features. Models trained with this algorithm are able to extract a higher number of distinct complex features in the deeper layers, and are able to recognize handwritten characters more accurately. Analysis in multidimensional vector space suggests that when the influence of the extended and strong features is reduced, the integrated features vectors are projected into a "wider" space, and the overlapping between the vectors is reduced. This explains the improved differentiation between distinct classes of vectors and the higher accuracy of recognition. We also investigated the use of information theory as an objective measure of the competence of neocognitron as a pattern classifier and recognizer. | |
dc.source | CCK BATCHLOAD 20200626 | |
dc.type | Thesis | |
dc.contributor.department | PHYSICS | |
dc.contributor.supervisor | LIM HOCK | |
dc.contributor.supervisor | BERNARD TAN | |
dc.description.degree | Master's | |
dc.description.degreeconferred | MASTER OF SCIENCE | |
Appears in Collections: | Master's Theses (Restricted) |
Show simple item record
Files in This Item:
File | Description | Size | Format | Access Settings | Version | |
---|---|---|---|---|---|---|
B18975501.PDF | 3.53 MB | Adobe PDF | RESTRICTED | None | Log In |
Google ScholarTM
Check
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.