A new learning strategy for time-series prediction using radial basis funct
ion (RBF) networks is introduced. Its potential is examined in the particul
ar case of the resource allocating network model, although the same ideas c
ould apply to extend any other procedure. In the early stages of learning,
addition of successive new groups of RBFs provides an increased rate of con
vergence. At the same time, the optimum lag structure is determined using o
rthogonal techniques such as QR factorization and singular value decomposit
ion (SVD). We claim that the same techniques can be applied to the pruning
problem, and thus they are a useful tool for compaction of information. Our
comparison with the original RAN algorithm shows a comparable error measur
e but much smaller-sized networks. The extra effort required by QR and SVD
is balanced by the simplicity of only using least mean squares for the iter
ative parameter adaptation. (C) 2001 Elsevier Science B.V. All rights reser
ved.