Task Decomposition through Competition in A

A novel modular connectionist architecture is presented in which the networks composing the architecture compete to learn the training patterns. An outcome of the competition is that di erent networks learn di erent training patterns and, thus, learn to compute di erent functions. The architecture performs task decomposition in the sense that it learns to partition a task into two or more functionally independent tasks and allocates distinct networks to learn each task. In addition, the architecture tends to allocate to each task the network whose topology is most appropriate to that task. The architecture's performance on \what" and \where" vision tasks is presented and compared with the performance of two multi{layer networks. Finally, it is noted that function decomposition is an underconstrained problem and, thus, di erent modular architectures may decompose a function in di erent ways. We argue that a desirable decomposition can be achieved if the architecture is suitably restricted in the types of functions that it can compute. Appropriate restrictions can be found through the application of domain knowledge. A strength of the modular architecture is that its structure is well{suited for incorporating domain knowledge.