Reports on the characteristics of a net which incorporates higher-order effects in supervised learning in ways different from those previously proposed. These higher-order effects are introduced through nonlinear functional transforms via links rather than at nodes. Specific instances include transforming the input vector into higher-order tensors. Learning-rate increases, for several examples, are described. Network architecture simplifications are also described.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
No takes yet. Share an insight, caveat, or question.
Klassen et al. (1988) studied this question.