In-situ learning in multi-net systems

Abstract

Multiple classifier systems based on neural networks can give proved generalisation performance as compared with single classifier systems. We examine collaboration in multi-net systems through in-situ learning exploring how generalisation can be improved through the simultaneous learning in networks and their combination. We present two in-situ trained systems; first, one based upon the simple ensemble, combining supervised networks in parallel, and second, a combination of unsupervised and supervised networks in, sequence. Results for these are compared with existing approaches demonstrating that in-situ trained systems perform better than similar pre-trained systems.

Document Downloads