神经网络课5-2教案 Chapter 5 Feedback Neural Network 研究生课件.pptVIP

5.2 BAM Network Chapter 6 ANN Hybrid System 6.1 Fuzzy Neural Network 6.2 Evolutionary Computation and Genetic Algorithm 6.3 A Hybrid System of Expert Systems and Neural Networks 6.1 Fuzzy Neural Network A. Fuzzy set B. Conversion Between Numeric and Fuzzy-Logic Variables C. Union and Intersection of Fuzzy sets D. Fuzzy Control Control rule table 2. Neural-Fuzzy Networks 3. Fuzzy Neural Network 6.2 Evolutionary Computation and Genetic Algorithm GA basic operation Practice 6.3 A Hybrid System of Expert Systems and Neural Networks 2. Neural networks versus expert systems 3. Advantages and limitations of expert systems and neural networks 4. An illustration of an expert network * Bidirectional Associative Memory 1 2 n … 1 2 m … a1 W2 w11 w21 W1 w11 b1 1 2 b2 bm m a2 an w11 Layer A Layer B 1 2 n … 1 2 m … x1 x2 xn y1 y2 ym Layer A W1 Layer B W2 x(t)=fy(fx(x(t-1)W1)W2) y(t)=fx(fy(y(t-1)W2)W1) w1 fx(x(t-1)w1) fy(y(t-1)w2) w2 x(t-1) x(t) y(t-1) Calculating process w1 fx(x(t-1)w1) fy(y(t-1)w2) w2 y(t-1) x(t-1) y(t) Assuming: x?{-1,+1}N, y ?{-1,+1}M (xi , yi), i=1,2,…,P Learning rule Definition of energy function: wi is the ith row weight factors in the W wj is the jth column weight factors in the W If ?xi0 then ywiT0 If ?xi0 then ywiT0 Therefore, ?E0 Hebb learning formular W1=W2T Example 1 x1(1 0 1 0 1) , y1(1 1 1 1) x2(1 0 1 0 0) , y2(0 1 1 0) x3(0 1 0 1 1) , y3(1 0 0 1) Change the vectors to {-1,+1} x1’(1 -1 1 -1 1) , y1’(1 1 1 1) x2’(1 -1 1 -1 -1) , y2’(-1 1 1 -1) x3’(-1 1 -1 1 1) , y3’(1 -1 -1 1) sgn(x1W)=sgn(1 5 5 1)=y1 sgn(y1WT)=sgn(4 –4 4 –4 4) =(1 –1 1 –1 1) change to binary sgn(y1WT)=(1 0 1 0 1)=x1 ?=(0 1 0 0 0) x1+ ?=(1 1 1 0 1) sgn[(x1+ ?)W]=sgn[2 2 2 2] =y1 Neural-fuzzy networks implements fuzz-logic inferencing through neural networks. 1. Fuzzy-logic Systems Fuzzy logic grew out of a desire to quantify rule-based systems. It provides a w