Improvement of pattern learning and recognition capability in ratio-memory cellular neural networks with non-discrete-type Hebbian learning algorithm

A ratio-memory cellular neural networks (RMCNN) with non-discrete-type Hebbian learning algorithm to learn and recognize image patterns is proposed and analyzed. In the proposed RMCNN, the space-variant A templates with self-feedback coefficients are determined from the trained patterns using the non-discrete-type Hebbian learning algorithm during the learning period. The determined A templates stored in the ratio memory are used in the RMCNN to recognize the learned patterns with different Gaussian noise levels and output the correct patterns. The operation of the proposed RMCNN has been simulated with Matlab software. It is shown that the 9×9 RMCNN can successfully learn recognize 23 noisy patterns with Gaussian noise variance of 0.3. As compared to other learnable CNNs as associative memories, the proposed RMCNN with a non-discrete-type Hebbian learning algorithm and 5 coefficients in the A template can learn and recognize many more patterns. With an improved pattern learning and recognition capability, the proposed RMCNN still can be implemented in VLSI for various applications.