This article describes a novel neural network structure designed for the dynamic classiica-tion of spatio-temporal signals. The network is a two-stage structure consisting of a biologically motivated temporal encoding stage followed by a static neural classiier stage. The temporal encoding stage is based upon a simple biological learning mechanism known as habituation. This habituation based ne...

This paper examines two-stage techniques for learning kernels based on a notion of alignment. It presents a number of novel theoretical, algorithmic, and empirical results for alignmentbased techniques. Our results build on previous work by Cristianini et al. (2001), but we adopt a different definition of kernel alignment and significantly extend that work in several directions: we give a novel...

We investigate the viability of a two-stage innationary scenario in the context of super-gravity, so as to resolve the problem of initial conditions for hybrid innation. We allow for non-renormalizable terms in the superpotential and consider the most general form of the KK ahler potential and the gauge kinetic function. We construct a model with two stages of innation, the rst driven by D-term...