Slow feature discriminant analysis and its application on handwritten digit recognition
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Learning invariant visual shape representations from physics
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Nonlinear dimensionality reduction using a temporal coherence principle
Information Sciences: an International Journal
Regularized sparse Kernel slow feature analysis
ECML PKDD'11 Proceedings of the 2011 European conference on Machine learning and knowledge discovery in databases - Volume Part I
Invariant object recognition and pose estimation with slow feature analysis
Neural Computation
Hi-index | 0.00 |
Invariant object recognition is arguably one of the major challenges for contemporary machine vision systems. In contrast, the mammalian visual system performs this task virtually effortlessly. How can we exploit our knowledge on the biological system to improve artificial systems? Our understanding of the mammalian early visual system has been augmented by the discovery that general coding principles could explain many aspects of neuronal response properties. How can such schemes be transferred to system level performance? In the present study we train cells on a particular variant of the general principle of temporal coherence, the “stability” objective. These cells are trained on unlabeled real-world images without a teaching signal. We show that after training, the cells form a representation that is largely independent of the viewpoint from which the stimulus is looked at. This finding includes generalization to previously unseen viewpoints. The achieved representation is better suited for view-point invariant object classification than the cells’ input patterns. This property to facilitate view-point invariant classification is maintained even if training and classification take place in the presence of an – also unlabeled – distractor object. In summary, here we show that unsupervised learning using a general coding principle facilitates the classification of real-world objects, that are not segmented from the background and undergo complex, non-isomorphic, transformations.