Off-line memory reprocessing following on-line unsupervised learning strongly improves recognition performance in a hierarchical visual memory.
Jenia JitsevChristoph von der MalsburgPublished in: IJCNN (2010)
Keyphrases
- unsupervised learning
- recognition accuracy
- computing power
- object recognition
- memory usage
- memory requirements
- supervised learning
- memory size
- random access
- main memory
- high level
- feature extraction
- pattern recognition
- working memory
- memory space
- limited memory
- long term memory
- learning stage
- data sets
- visual perception
- hierarchical structure
- operating system
- model selection
- recognition rate
- semi supervised
- learning algorithm