High-order two-dimension cluster competitive activation mechanisms used for performing symbolic logic algorithms of problem solving
- 15 Downloads
This paper presents a neural network approach, based on high-order two-dimension temporal and dynamically clustering competitive activation mechanisms, to implement parallel searching algorithm and many other symbolic logic algorithms. This approach is superior in many respects to both the common sequential algorithms of symbolic logic and the common neural network used for optimization problems. Simulations of problem solving examples prove the effectiveness of the approach.
KeywordsHigh-order temporal network competitive activation symbolic logic algorithm dynamic clustering optimization problem
Unable to display preview. Download preview PDF.
- Fahner G. An algorithm-structured neural net for the shortest-path problem. InProc. of IJCNN'91, I: 153–158.Google Scholar
- Fahner G. A high order unit that performs arbitrary Boolean function. InProc. of IJCNN'90, III: 193–197.Google Scholar
- Benain M, Samuelides M. Dynamic properties of neural nets using competitive activation mechanism. InProc. of IJCNN'90, III: 541–546.Google Scholar
- Shuai Dianxun. A new microprocessor for fast parallelly solving the LCS problem.Chinese Journal of Computers, 1985, 8(3): 223–236.Google Scholar