Memory capacity of terminal attractor optical associative memory

نویسندگان

  • Xin Lin
  • Junji Ohtsubo
چکیده

The memory 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 the computer simulations, we give intuitive estimates of the memory capacity of the TA model associative memory. For the feasibility of the optical implementation of the TA associative memory, we impose some approximations to original TA associative memory without loosing the essence of the TA model. The memory capacity of such a modified TA model associative memory is also given by the numerical simulation. In this simulation, a 10×10 neuron network model is used and Hamming distances among inputs and the stored patterns are chosen to be equal to 5 or more both in the original and modified TA models. The results indicate that the absolute memory capacity of the TA model is greater than 0.35N, which contrasts with the relative capacity of 0.15N or the theoretical absolute capacity of for the conventional associative memory. xi m ( ) xi N / (4 N ln )

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Terminal Attractor Optical Associative Memory for Pattern Recognition

Optical associative memory with terminal attractor (TA) is proposed for pattern recognition. With numerical simulations, the optimal control parameter in the TA model associative memory is determined. The optimal control parameter is also used in an optical experiment. The capacity of TA model associative memory is also investigated based on the consistency between the stored pattern and the ob...

متن کامل

Sign Constrained High Capacity Associative Memory Models

Biological neural networks do not allow the synapses to choose their own sign: excitatory or inhibitory. The consequences of imposing such a sign-constraint on the weights of the standard Hopfield associative memory architecture, trained using perceptron like learning, are examined in this paper. The capacity and attractor performance of these networks is empirically investigated, with sign-con...

متن کامل

High Performance Associative Memory and Sign Constraints

The consequences of imposing a sign constraint on the standard Hopfield architecture associative memory model, trained using perceptron like learning rules, is examined. Such learning rules have been shown to have capacity of at most half of their unconstrained versions. This paper reports experimental investigations into the consequences of constraining the sign of the network weights in terms...

متن کامل

High Performance Associative Memories and Structured Weight Dilution

The consequences of two techniques for symmetrically diluting the weights of the standard Hopfield architecture associative memory model, trained using a non-Hebbian learning rule, are examined. This paper reports experimental investigations into the effect of dilution on factors such as: pattern stability and attractor performance. It is concluded that these networks maintain a reasonable leve...

متن کامل

Unipolar Terminal-attractor Based Neural Associative Memory with Adaptive Threshold

J. J. Hopfield, “Neural Networks and Physical Systems with Emergent Collective Computational Abilities,” Proc. Nat. Acad. Sci., USA, vol. 79, pp. 2254-2258, Apr. 1982. R. J. McEliece, et al., “The Capacity of the Hopfield Associative Memory,” IEEE Transactions on Information Theory, vol. T-33, pp. 461-482, 1987. B. L. Montgomery et al., “Evaluation of the use of Hopfield Neural Network Model as...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2016