Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
We propose a new approach to value-directed belief state approximationfor POMDPs. The valuedirected model allows one to choose approximation methods for belief state monitoringtha...
Volume rendering is a widespread method for displaying graphical models in fields such as medical visualization or engineering. The required image information is stored in a volum...
This paper introduces a new model of a spiking neuron with active dendrites and dynamic synapses (ADDS). The neuron employs the dynamics of the synapses and the active properties ...
This paper deals with the adaptive control of a class of continuous-time nonlinear dynamic systems preceded by an unknown dead-zone. By using a new description of a dead-zone and ...