Aspects of the Binary CMAC: Unimodularity and Probabilistic Reconstruction
Neural Processing Letters
Cybernetics and Systems Analysis
Choosing an information coding scheme for a CMAC neural network
Cybernetics and Systems Analysis
Closed-loop method to improve image PSNR in pyramidal CMAC networks
International Journal of Computer Applications in Technology
Expert Systems with Applications: An International Journal
A novel associative memory approach to speech enhancement in a vehicular environment
Expert Systems with Applications: An International Journal
Direct inverse model control based on a new improved CMAC neural network
ICIC'10 Proceedings of the 6th international conference on Advanced intelligent computing theories and applications: intelligent computing
A balanced learning CMAC neural networks model and its application to identification
ICIC'06 Proceedings of the 2006 international conference on Intelligent Computing - Volume Part I
The improved CMAC model and learning result analysis
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Hi-index | 0.02 |
A hierarchical coding system for progressive image transmission that uses the generalization and learning capability of CMAC (cerebellar model arithmetic computer or cerebellar model articulation controller) is described. Each encoder and decoder includes a set of CMACs having different widths of generalization region. A CMAC with a wider generalization region is used to learn a lower frequency component of the original image. The training signals for each CMAC are progressively transmitted to a decoder. Compression is achieved by decreasing the number of training signals for CMAC with a wider generalization region, and by making quantization intervals wider for CMAC with a smaller generalization region. CMACs in the decoder are trained on the training signals to be transmitted. The output is recursively added to the other so that the quality of image reconstruction is gradually improved. The proposed method, unlike the conventional hierarchical coding methods, uses no filtering technique in both decimation and interpolation processes, and has the following advantages: (i) it does not suffer from problems of blocking effect; (ii) the computation includes no multiplication; (iii) the coarsest reconstructed image is quickly produced; (iv) the total number of transmitted data is equal to the number of the original image pixels; (v) all the reconstructed images are equal to the original image in size; (vi) quantization errors introduced at one level can be taken into account at the next level, allowing lossless progressive image transmission