Yield curve forecasting by error correction neural networks and partial learning

Error correction neural networks (ECNN) are an appropriate framework for the modeling of dynamical systems in the presents of noise or missing external innuences. Combining ECNNs with the concept of variants-invariants separation in form of a bottleneck coordinate transformation, we are able to handle high-dimensional problems. Further on, we propose a new learning rule for the training of neural networks, which e v aluates only speciic gradients for the adaptation of the network weights. By this, we are able to generate time invariant localized structures and thus, support the optimization of the network. Forecasting the German yield curve, an ECNN including the separation of variants-invariants is superior to traditional neural networks.