A Hierarchical Incremental Learning Approach To Task Decomposition

In this paper, we suggest a new task decomposition method of hierarchical incremental class learning (HICL). In this approach, a K -class problem is divided into K subproblems. The sub-problems are leamt sequentially in a hierarchical structure with K sub-networks. Each sub-network takes the output from the sub-network immediately below it as well as the original input as its input. The output from each sub-network contains one more class than the sub-network immediately below it, and this output is fed into the sub-network above it. It not only reduces harmful interference among hidden layers, buf also facilities information transfer between classes during training. The later sub-networks can obtain learnt information from the earlier sub-networks. We also proposed two ordering algorithms of MSEF and MSEF-FLD to determine the hierarchical relationship between the sub-networks. HICL approach shows smaller regression error and classification error than the class decomposition and retraining approaches.