机译:增强的模糊最小-最大神经网络用于模式分类
Sch. of Electr. & Electron. Eng., Univ. Sci. Malaysia, Nibong Tebal, Malaysia;
fuzzy neural nets; learning (artificial intelligence); minimax techniques; pattern classification; EFMM network; classification performance; enhanced fuzzy min-max neural network; heuristic rules; hyperbox contraction rule; hyperbox expansion process; hyperbox expansion rule; hyperbox overlap test rule; learning algorithm; overlapping cases; overlapping problem; pattern classification problems; Adaptation models; Artificial neural networks; Biological system modeling; Learning systems; Subspace constraints; Training; Fuzzy min-max (FMM) model; Fuzzy min???max (FMM) model; hyperbox structure; neural network learning; pattern classification; pattern classification.;
机译:通用模糊最小-最大神经网络用于模式分类问题的比较研究
机译:一种精致的模糊MIN-MAX神经网络,具有模式分类的新学习程序
机译:模糊最小-最大神经网络在模式分类中的应用及其应用
机译:使用改进的增强型模糊最小-最大神经网络的模式分类
机译:用关系模糊神经网络和平方BK增强模式分类
机译:具有权重稀疏控制和预训练的深度神经网络可提取分层特征并增强分类性能:来自精神分裂症的全脑静止状态功能连接模式的证据
机译:增强的模糊最小最大神经网络的集成,用于数据分类
机译:神经网络计算:多层感知器与分层模式识别网络的分类问题比较