6.3 Synaptic convergence to centroids:AVQ Algorithms Differential Competitive Learning (DCL) m,(t+1)=m,(t)+c,AS,(y,(t)[x(t)-m,(t)] m,(t+1)=m,(t) fi≠j AS((denotes the time change of the jth neuron'scompetitive signal S AS,(y,(t)=S,(y,(t+1)-S,(y,(t) In practice we often use only the sign of the signal difference or sgn[Ay,], the sign of the activation difference. 2003.11.19 122003.11.19 12 6.3 Synaptic convergence to centroids: AVQ Algorithms ( ) S y j j sgn[ ] j y Differential Competitive Learning (DCL) ( 1) ( ) ( ( ))[ ( ) ( )] ( 1) ( ) j j t j j j i i m t m t c S y t x t m t m t m t if i j + = +  − + =  ( ( )) j j S y t denotes the time change of the jth neuron’s competitive signal ( ( )) ( ( 1)) ( ( ))  = + − S y t S y t S y t j j j j j j In practice we often use only the sign of the signal difference or , the sign of the activation difference