Related Experiment Videos
On the uniqueness of weights in single-layer perceptrons
1Dept. of Electr. and Comput. Eng., Carnegie Mellon Univ., Pittsburgh, PA.
Abstract:
In this paper the geometric formulation of the single layer perceptron weight optimization problem previously described by Coetzee et al. (1993, 1996) is combined with results from other researchers on nonconvex set projections to describe sufficient conditions for uniqueness of weight solutions. It is shown that the perceptron data surface is pseudoconvex and has infinite folding, allowing for the specification of a region of desired vectors having unique projections purely in terms of the local curvature of the data surface. No information is therefore required regarding the global curvature or size of the data surface. These results in principle allow for a posteriori evaluation of whether a weight solution is unique or globally optimal, and for a priori scaling of desired vector values to ensure uniqueness, through analysis of the input data. The practical applicability of these results from a numerical perspective is evaluated on some carefully chosen examples.
Related Concept Videos
Weighted Mean
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
Second Uniqueness Theorem
In contrast, consider that the electric field is non-unique and apply Gauss's law in divergence form in the region between the conductors and the integral form to the surface...
Apparent Weight
Consider a person standing on a bathroom scale inside an elevator. If the scale is accurate at rest, its reading equals the...
Significance of the Gradient Vector
Mass and Weight
Mass and Weight