Distributed key-generation structures for associative image-classification

Associative memories can be utilized in image classification to provide robustness and noise insensitivity. On the other hand, real-time applications demand fast performance at all steps of associative coding. In the present work, the noise-like coding model of an associative memory is adopted, and a general architecture for the key-generation process is described. The fractal property of Peano curves is exploited to define a structure which performs distributed computations; this facilitates the system's implementation on parallel architectures, and also notably improves the associative system's performance.<<ETX>>

[1]  Dean Pomerleau,et al.  Efficient Training of Artificial Neural Networks for Autonomous Navigation , 1991, Neural Computation.

[2]  Rodolfo Zunino,et al.  Speeding up scene recognition by using an associative noise-like coding memory , 1991, [1991 Proceedings] Tenth Annual International Phoenix Conference on Computers and Communications.

[3]  Arthur R. Butz,et al.  Alternative Algorithm for Hilbert's Space-Filling Curve , 1971, IEEE Transactions on Computers.

[4]  Rodolfo Zunino,et al.  Image classification by using associative noise-like coding memories , 1990, Ninth Annual International Phoenix Conference on Computers and Communications. 1990 Conference Proceedings.

[5]  Davide Anguita,et al.  Transputer-based architectures for associative image classification , 1991, Proceedings of the Third IEEE Symposium on Parallel and Distributed Processing.

[6]  Geoffrey E. Hinton,et al.  Parallel Models of Associative Memory , 1989 .