This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different views. Multinomial logit model is used for the viewpoin...

Viewpoints are re ections of software systems from multiple perspectives. A number of consistency conditions apply to viewpoints and developers require a tool for each type of viewpoint. These tools need to support consistency management. Inter-viewpoint consistency can only be checked when tools are integrated into a viewpoint development environment. We brie y outline the functionality develo...

a dialogue between myself and my hallucinations. The publication of this book brought me letters from people who wanted to know how a nurse could work efficiently while being a schizophrenic. Getting the schizophrenic a job and helping him to keep it are very important tasks for psychiatrists and social workers. The way has been paved by the setting up of workshops within hospitals, so that pat...

Experiencing a body part as one's own, i.e., body ownership, depends on the integration of multisensory bodily signals (including visual, tactile, and proprioceptive information) with the visual top-down signals from peripersonal space. Although it has been shown that the visuo-spatial viewpoint from where the body is seen is an important visual top-down factor for body ownership, different stu...