作者: Vitoantonio Bevilacqua , Fabio Cassano , Ernesto Mininno , Giovanni Iacca
DOI: 10.1007/978-3-319-32695-5_5
关键词:
摘要: The design of robust classifiers, for instance Artificial Neural Networks (ANNs), is a critical aspect in all complex pattern recognition or classification tasks. Poor choices may undermine the ability system to correctly classify data samples. In this context, evolutionary techniques have proven particularly successful exploring state-space underlying ANNs. Here, we report an extensive comparative study on application several modern Multi-Objective Evolutionary Algorithms and training ANN samples from two different biomedical datasets. Numerical results show that algorithms strengths weaknesses, leading ANNs characterized by levels accuracy network complexity.