Well-Behaved, Smooth Representations are Critical

Representation is critical in the ARL system since it must be carefully selected to achieve learning. Invariance in the system must be introduced a priori into the representation. For example, if a feature is spurious and contributes no information about the interaction, it will waste resources. The system will wastefully attempt to model and predict it inside the ${\bf y}$ vector. In addition, the representations must be smooth and must not have ambiguities. For example, during initial phases of development, the ARL system employed a different representation of the head and hand blobs. The head and hands were described by their mean, major axis, minor axes and rotation (in radians). Unlike the square-root covariance shape descriptor (our current representation), the rotation value had some unusual singularities. The 0 and $2\pi$ values are identical in radian notation. Thus, the system would generate non-linear steps from 0 to $2\pi$ as the blobs would rotate and these transitions were difficult to span using the eigenspace temporal processing techniques. Thus, it is critical to pick a representation which contains the desired invariants, is well behaved, is smooth and has no spurious components.