Learning by gradient descent in function space

The use of connectionist networks in which each node executes a different function to achieve efficient supervised learning is demonstrated. A modified backpropagation algorithm for such networks, which performs gradient descent in function space, is presented, and its advantages are discussed. The benefits of the suggested paradigm include faster learning and ease of interpretation of the trained network. The potential for combining this approach with other related approaches, including traditional backpropagation or reweighting is explored