An Incremental Learning Structure using Granular Computing and Model Fusion With Application to Materials Processing

This paper introduces a neural-fuzzy (NF) modeling structure for offline incremental learning. Using a hybrid model updating algorithm (supervised/unsupervised) this NF structure has the ability to adapt in an additive way to new input-output mappings and new classes. Data granulation is utilised along with a NF structure to create a high performance yet transparent model that entails the core of the system. A model fusion approach is then employed to provide the incremental update of the system. The proposed system is tested against a multidimensional modeling environment consisting of a complex, non-linear and sparse database