An adaptive history network method to improve the genetic optimization of pattern recognition systems

The existence of many pattern recognition systems (PRSs) and their relative merits and drawbacks highlights the need for a metalearning framework that can find the best PRS method for a given task. To address this issue, a hyperparameter evolutionary optimization (HPEO) framework was previously devised, initially using a genetic algorithm to tune external PRS parameters in a modular fashion, decoupled from its internal components. To further improve the effectiveness of HPEO and improve the diversity of the hyperparameter solutions found, this paper presents an extension that realizes cross-generation learning with an adaptive history network (AHN), which promotes exploring new regions in the search space while avoiding regions that have been searched extensively. The proposed approach, termed HPEO-AHN, is particularly suitable for tuning powerful but complex PRSs such as neuro-fuzzy systems (NFS). Preliminary experiments with two state-of-the-art NFSs optimized using the new approach have shown encouraging results.