“…In order to have the higher order non-linear correlation among input patterns, extensive attempts have been made by Giles and Maxwell (1987), Xu et al (1992), Zhang et al (2002), Homma et al (2003) and Kalra et al (2003) to develop the higher order neurons. Motivated by their efforts, a class of structures known as pi-sigma [12], [13], second order neuron [14], generalized neurons [15], [16], [9] and other higher order neurons [17], [18] and functional link networks [19], [20] have been introduced. Though, higher order neurons have proved to be most efficient, but they suffer from the typical curse of dimensionality due to combinatorial explosion of terms, demanding sparseness in the represen tation.…”