朝阳科技大学李丽华教授朝阳-LMS.PPT

-Artificial Neural Network- Bidirectional Associative Memory (BAM) 朝陽科技大學 資訊管理系 李麗華 教授 朝陽科技大學 李麗華 教授 * Introduction Bidirectional Associative Memory (BAM) was proposed by Bart Kosko in 1985. It is a hetro-associative memory network. It allows the network to memorize from a set of pattern Xp to recall another set of pattern Yp Y1 Y2 Ym ?????? ??????? 朝陽科技大學 李麗華 教授 * Assoicative Memory (AM) 1 Def: Associative memory (AM) is any device that associates a set of predefined output patterns with specific input patterns. Two types of AM: Auto-associative Memory: Converts a corrupted input pattern into the most resembled input. Hetro-associative Memory: Produces an output pattern that was stored corresponding to the most similar input pattern. 朝陽科技大學 李麗華 教授 * Models: It is the associative mapping of an input vector X into the output vector V. EX: Hopfield Neural Network (HNN) EX: Bidirectional Associative Memory (BAM) Assoicative Memory (AM) 2 Assoicative Memory X1 X2 X3 : Xn v1 v2 v3 : vm 朝陽科技大學 李麗華 教授 * BAM Architecture Input layer： Output layer： Weights： Connection： Y1 Y2 Ym ?????? ??????? It’s a 2-layer, fully connected, feed forward feed back network. 朝陽科技大學 李麗華 教授 * BAM Architecture (cont.) Transfer function： 朝陽科技大學 李麗華 教授 * BAM Example(1/4) Test pattern Y1 Y 2 Y3 Y4 1 -1 1 -1 1 -1 1 -1 1 -1 -1 1 -1 1 -1 1 -1 1 -1 1 1 1 1 1 1 1 -1 -1 -1 1-1 -1 -1 -1 -1 -1 -1 1 1 1 1 ●●● ○●○ ● ○● ○● ○ ○●○●○● ● ●● ● ●● ○ ○○ ○ ○○ 朝陽科技大學 李麗華 教授 * BAM Example(2/4) 1. Learning Set up network Setup weights Y1 Y 2 Y3 Y4 1 -1 1 -1 1 -1 1 -1 1 -1 -1 1 -1 1 -1 1 -1 1 -1 1 1 1 1 1 1 1 -1 -1 -1 1-1 -1 -1 -1 -1 -1 -1 1 1 1 1 朝陽科技大學 李麗華 教授 * BAM Example(3/4) 2. Recall Read network weights Read test pattern Compute Y Compute X Repeat (3) (4) until converge 朝陽科技大學 李麗華 教授 * BAM Example(4/4) 聚類之Application No1 (1) No2 (2) 二次都相同 test pattern (1 1 1 -1 1 -1)1*6 ? ●●● ○●○