Supervised Self-Co ing in Multilayere Feedforward Networks
Ramesh R. Sarukkai · 1996
AbstructSupervised neural-network learning algorithms have proven very successful at solving a variety of learning problems. However, they suffer from a common problem of requiring explicit output labels. This requirement makes such algorithms implausible as biological models. In this paper, it is shown that pattern classification can be achieved, in a multilayered feedforward neural network, without requiring explicit output labels, by a process of supervised selj-coding. The class projection is achieved by optimizing appropriate within-class uniformity, and between-class discernibility criteria. The mapping function and the class labels are developed together, iteratively using the derived selfcoding backpropagation algorithm. The ability of the self-coding network to generalize on unseen data is also experimentally evaluated on real data sets, and compares favorably with the traditional labeled supervision with neural networks. However, interesting features emerge out of the proposed seljcoding supervision, which are absent in conventional approaches. The further implications of supervised self-coding with neural networks are also discussed.