Improving the Associative Rule Chaining Architecture
This paper describes improvements to the rule chaining architecture presented in . The architecture uses distributed associative memories to allow the system to utilise memory efficiently, and superimposed distributed representations in order to reduce the time complexity of a tree search to O(d), where d is the depth of the tree. This new work reduces the memory required by the architecture, and can also further reduce the time complexity.
Keywordsrule chaining correlation matrix memory associative memory distributed representation parallel distributed computation
Unable to display preview. Download preview PDF.
- 2.Kohonen, T.: Correlation Matrix Memories. IEEE Transactions on Computers, 353–359 (1972)Google Scholar
- 3.Gorodnichy, D.O.: Associative Neural Networks as Means for Low-Resolution Video-Based Recognition. IJCNN 2005, 3093–3098 (2005)Google Scholar
- 4.Ju, Q., O’Keefe, S., Austin, J.: Binary Neural Network Based 3D Facial Feature Localization. IJCNN 2009, 1462–1469 (2009)Google Scholar
- 7.Austin, J.: Parallel Distributed Computation in Vision. IEE Colloquium on Neural Networks for Image Processing Applications, 3/1–3/3 (1992)Google Scholar
- 9.Palm, G.: On the Storage Capacity of Associative Memories. In: Neural Assemblies, an Alternative Approach to Artificial Intelligence, pp. 192–199. Springer, New York (1982)Google Scholar