Capacity of optical associative memory using a terminal attractor model
暂无分享,去创建一个
Abstract The capacity of terminal attractor (TA) model associative memory is investigated based on the consistency between the stored pattern and the obtained equilibrium state in statistical thermodynamics. By computer simulations, we give intuitive estimates of the capacity of the TA model associative memory. For feasibility of optical implementation of the TA associative memory, we impose some approximations to the original TA associative memory without losing the essence of the TA model. The capacity of such a modified TA model associative memory is also given by numerical simulation. The results indicate that the absolute capacity of the TA model is greater than 0.35 N , which contrasts with the relative capacity of 0.15 N or the theoretical absolute capacity of N /(4 ln N ) for the conventional associative memory.
[1] M. Zak. Terminal attractors in neural network , 1989 .
[2] J Ohtsubo,et al. Real-time optical image subtraction and edge enhancement using ferroelectric liquid-crystal devices based on speckle modulation. , 1996, Applied optics.
[3] Xin Lin,et al. Optical neural networks with terminal attractors for pattern recognition , 1996 .
[4] B V Kumar,et al. Evaluation of the use of the Hopfield neural network model as a nearest-neighbor algorithm. , 1986, Applied optics.