Browsing by Author "CHANG, JY"

Now showing 1 - 9 of 9

A HIGH SPEED REED-SOLOMON CODEC CHIP USING LOOKFORWARD ARCHITECTURE
(1994)
CHANG, JY
;
SHUNG, CB
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
A NEW 2-D ZERO PHASE DIGITAL FILTER DESIGN WITH QUADRANTALLY SYMMETRIC OR ANTISYMMETRIC PROPERTIES
(1994)
CHANG, JY
;
WANG, WH
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A NEW LOCAL TRAINING RULE FOR HIGHER-ORDER ASSOCIATIVE MEMORIES
(1994)
CHANG, JY
;
LIU, WH
;
LIN, JK
;
電控工程研究所
;
Institute of Electrical and Control Engineering
DESIGN OF HOPFIELD-TYPE ASSOCIATIVE MEMORY WITH MAXIMAL BASIN OF ATTRACTION
(1993-11-25)
CHANG, JY
;
WU, CC
;
交大名義發表
;
電控工程研究所
;
National Chiao Tung University
A method is described for enlarging as much as possible the basin of attraction of a Hopfield-type associative memory. The proposed learning rule, a minimum-overlap learning algorithm that includes a threshold parameter, enables a Hopfield-type associative memory to be designed so that the memory will have a maximal basin of attraction. A technique that diminishes the effect of the threshold on the minimum-overlap learning algorithm is devised. Simulation results show that the basin of attraction constructed by the proposed method is indeed larger than that constructed by several well known methods.
IMAGE SEQUENCE CORRESPONDENCE VIA A HOPFIELD NEURAL-NETWORK
(1993-07-01)
CHANG, JY
;
LEE, SW
;
HORNG, MF
;
電控工程研究所
;
Institute of Electrical and Control Engineering
A neural network approach to finding trajectories of feature points in a monocular image sequence is proposed. In conventional methods, this problem is formulated as an optimization problem and solved using heuristic algorithms. The problem usually involves lengthy computations, making it computationally difficult. We apply the Hopfield neural network to image sequence correspondence. The design and development of the Lyapunov function for this problem are discussed in detail. Furthermore, the neural-network-based image correspondence scheme is extended to the case of successive image frames, in which some feature points are allowed to be occluded. Examples and simulation results are presented to illustrate the design process and the convergence characteristics of the proposed neural network. By using the massive parallel-processing power of neural networks, a real-time and accurate solution can be obtained.
INVARIANT PATTERN-RECOGNITION USING HIGHER-ORDER NEURAL NETWORKS
(1993)
WU, J
;
CHANG, JY
;
電控工程研究所
;
Institute of Electrical and Control Engineering
MODEL-REDUCTION FOR CONTINUOUS-TIME AND DISCRETE-TIME-SYSTEMS VIA SQUARED-MAGNITUDE RESPONSES MATCHING BY LINEAR-PROGRAMMING
(1991-04-01)
CHENG, MH
;
CHANG, JY
;
交大名義發表
;
電控工程研究所
;
National Chiao Tung University
The use of linear programming technique for the model reduction of continuous- and discrete-time systems is discussed. Based on squared-magnitude responses between the original system and its reduced model, a novel error function is presented. Two linear programming formulations are presented that use the L1-norm and the L infinity-norm of the proposed error function as respective criteria to solve the squared-magnitude problem. Finally, the reduced model is obtained by applying the factorization technique. Since the poles of the obtained squared-magnitude function are prevented from occurring on the j-omega axis (continous-time case) or unit circle (discrete-time case) by constraint, this approach ensures the stability of the reduced model. Some examples illustrate its applicability.
THE GENERALIZED WEIGHTED ASSOCIATIVE MEMORY
(1993)
YEH, B
;
CHANG, JY
;
WU, CC
;
電控工程研究所
;
Institute of Electrical and Control Engineering
THE PERCEPTRON TRAINING RULE FOR BIDIRECTIONAL ASSOCIATIVE MEMORY
(1993)
LIN, JK
;
CHANG, JY
;
電控工程研究所
;
Institute of Electrical and Control Engineering