Slow Feature Analysis: Perspectives for Technical Applications of a Versatile Learning Algorithm
| dc.contributor.author | Escalante-B., Alberto N. | |
| dc.contributor.author | Wiskott, Laurenz | |
| dc.date.accessioned | 2018-01-08T09:16:10Z | |
| dc.date.available | 2018-01-08T09:16:10Z | |
| dc.date.issued | 2012 | |
| dc.description.abstract | Slow Feature Analysis (SFA) is an unsupervised learning algorithm based on the slowness principle and has originally been developed to learn invariances in a model of the primate visual system. Although developed for computational neuroscience, SFA has turned out to be a versatile algorithm also for technical applications since it can be used for feature extraction, dimensionality reduction, and invariance learning. With minor adaptations SFA can also be applied to supervised learning problems such as classification and regression. In this work, we review several illustrative examples of possible applications including the estimation of driving forces, nonlinear blind source separation, traffic sign recognition, and face processing. | |
| dc.identifier.pissn | 1610-1987 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/11318 | |
| dc.publisher | Springer | |
| dc.relation.ispartof | KI - Künstliche Intelligenz: Vol. 26, No. 4 | |
| dc.relation.ispartofseries | KI - Künstliche Intelligenz | |
| dc.subject | Blind source separation | |
| dc.subject | Dimensionality reduction | |
| dc.subject | Driving forces | |
| dc.subject | Face processing | |
| dc.subject | Hierarchical networks | |
| dc.subject | High-dimensional data | |
| dc.subject | Nonlinear feature extraction | |
| dc.subject | Object recognition | |
| dc.subject | Slow feature analysis | |
| dc.title | Slow Feature Analysis: Perspectives for Technical Applications of a Versatile Learning Algorithm | |
| dc.type | Text/Journal Article | |
| gi.citation.endPage | 348 | |
| gi.citation.startPage | 341 |