Abstract. The Self-Organising Map (SOM) is a well-known neuralnetwork model that has successfully been used as a data analysis tool in many different domains. The SOM provides a to...
Abstract. A common practice to gain invariant features in object recognition models is to aggregate multiple low-level features over a small neighborhood. However, the differences ...
Abstract. We investigate the extent to which eye movements in natural dynamic scenes can be predicted with a simple model of bottom-up saliency, which learns on different visual re...
Eleonora Vig, Michael Dorr, Thomas Martinetz, Erha...
Kernelized LASSO (Least Absolute Selection and Shrinkage Operator) has been investigated in two separate recent papers (Gao et al., 2008) and (Wang et al., 2007). This paper is co...
Abstract. In many supervised learning tasks it can be costly or infeasible to obtain objective, reliable labels. We may, however, be able to obtain a large number of subjective, po...