Off-line performance maximisation in feed-forward neural networks by applying virtual neurons and covariance transformations

Optimisation of a feed-forward neural paradigm for a given application involves problems such as maximisation of the generalisation ability (relevant to provide effectiveness) and structure minimisation (allowing for physical realisability by using dedicated VLSI devices). This paper proposes a contemporaneous solution of these conflicting goals. The globally-optimised structure is identified by using a covariance matrix transformation and layers of virtual neurons