摘要
A reinforcement clustering framework which constitutes Bernoulli stochastic neural units is proposed inthis paper. Reinforcement learning mechanism is introduced to LVQ clustering problems. Related algorithm LVQ-Ris developed and its property is analyzed in detail. The authors conclude that reinforcement learning can be also intro-duced to other on-line competitive clustering methods. Experiments show that LVQ-R has better performance than o-riginal LVQ approach.
A reinforcement clustering framework which constitutes Bernoulli stochastic neural units is proposed in this paper. Reinforcement learning mechanism is introduced to LVQ clustering problems. Related algorithm LVQ-R is developed and its property is analyzed in detail. The authors conclude that reinforcement learning can be also introduced to other on-line competitive clustering methods. Experiments show that LVQ-R has better performance than o-riginal LVQ approach.
出处
《计算机科学》
CSCD
北大核心
2002年第12期133-134,132,共3页
Computer Science