Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide flexible decision borders. Networks based on such transfer functions should be small and accurate. Several possibilities of using transfer functions of different types in neural models are discussed, including enhancement of i...

Most direct volume renderings produced today employ onedimensional transfer functions, which assign color and opacity to the volume based solely on the single scalar quantity which comprises the dataset. Though they have not received widespread attention, multi-dimensional transfer functions are a very effective way to extract materials and their boundaries for both scalar and multivariate data...

Transfer functions are constantly used in both Seismology and Geotechnical Earthquake Engineering to relate seismic ground motion at different depths within strata. In the context of diffusive theory, they also appear expression imaginary part 1D Green’s functions. spite their remarkable importance, mathematical structure is not fully understood yet, except simplest cases two or three layers mo...