A massively parallel architecture for a self-organizing neural pattern recognition machine
Computer Vision, Graphics, and Image Processing
2-D Invariant Object Recognition Using Distributed Associative Memory
IEEE Transactions on Pattern Analysis and Machine Intelligence
Selective and Focused Invariant Recognition Using Distributed Associative Memories (DAM)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Parallel Models of Associative Memory
Parallel Models of Associative Memory
IEEE Transactions on Computers
Representation of Associated Data by Matrix Operators
IEEE Transactions on Computers
Associative holographic memories
IBM Journal of Research and Development
Hi-index | 0.00 |
In the noise-like coding model of associative memory, the core of the information-coding mechanism lies in the key-production process, by which a given pattern is transformed into a corresponding noise-like key for both information storage and retrieval. In this paper, it is shown how the pseudorandom behaviour typical of chaotic processes can be exploited to obtain noise-like patterns from supplied input patterns by a deterministic procedure. A mathematical analysis is carried out to prove the validity of the approach: It demonstrates that the generated patterns satisfy the noise-like constraints imposed by the associative model on keys. The main advantage is the possibility of performing computations at the local level. Experimental results confirm both the correctness of the theoretical derivations and the effectiveness of the proposed methodology in (visual) pattern classification applications.