Refereed full papers (journals, book chapters, international conferences)

1992

This report compares the representational capabilities of three-layer (that is, ``one hidden layer'') and four-layer (``two-hidden-layer'') nets consisting of feedforward interconnections of linear threshold units. It is remarked that for certain problems four layers are required, contrary to what might be in principle expected from the known approximation theorems. The differences are not based on numerical accuracy or number of units needed, nor on capabilities for feature extraction, but rather on a much more basic classification into ``direct'' and ``inverse'' problems. The former correspond to the approximation of continuous functions, while the latter are concerned with approximating one-sided inverses of continuous functions - and are often encountered in the context of inverse kinematics determination or in control questions. A general result is given showing that nonlinear control systems can be stabilized using four layers, but not in general using three layers.