Incremental backpropagation learning networks
LiMin Fu, Hui-Huang Hsu, José Carlos Príncipe · IEEE Transactions on Neural Networks · 1996
How to learn new knowledge without forgetting old knowledge is a key issue in designing an incremental-learning neural network. In this paper, we present a new incremental learning method for pattern recognition, called the "incremental backpropagation learning network", which employs bounded weight modification and structural adaptation learning rules and applies initial knowledge to constrain the learning process. The viability of this approach is demonstrated for classification problems including the iris and the promoter domains.