Capacity of Bidirectional Associative Memory
نویسنده
چکیده
The capacity of Bidirectional associative memory (BAM) was examined a lot in research, but not completely. In particular, this issue was not investigated in the context of strings coding. In this paper we apply different approaches to estimate the capacity of BAM for strings coding. One of these approaches is recalling of all coded strings. Another is applying Hamming and Levenshtein distances to recover coded strings. The experiments show poor performance of BAM for the problem of strings coding. In addition, we find a small example of poor performance of BAM. We also discover that there is its extended version. The examples can be used to test advanced methods of coding of strings. Subject Classification: 68T05
منابع مشابه
Generalized Asymmetrical Bidirectional Associative Memory*
A classical bidirectional associative memory (BAM) suffers from low storage capacity and abundance of spurious memories though it has the properties of good generalization and noise immunity. In this paper, Hamming distance in recall procedure of usual asymmetrical BAM is replaced with modified Hamming distance by introducing weighting matrix into connection matrix. This generalization is valid...
متن کاملStability and statistical properties of second-order bidirectional associative memory
In this paper, a bidirectional associative memory (BAM) model with second-order connections, namely second-order bidirectional associative memory (SOBAM), is first reviewed. The stability and statistical properties of the SOBAM are then examined. We use an example to illustrate that the stability of the SOBAM is not guaranteed. For this result, we cannot use the conventional energy approach to ...
متن کاملGenetic Algorithm Enlarges the Capacity of Associative Memory
We propose a genetic algorithm for mutually connected neural networks to obtain a higher capacity of associative memory. In Hop eld network as an associative memory system, the memory capacity is at most 15% of the number of neurons. Here we applied our method to the Hop eld network, and obtained the capacity of 33%. We conjectured that this is due to both asymmetry and sparseness of the connec...
متن کاملA statistical investigation of bidirectional associative memories (BAM)
We inve,tigate by ~tati,tical mechanical methods a uocha~tic analogue of the bidirectional a;sociative memone~ introduced by B. Kosko. We denve its ;torage capacity a~ a function of the total number of synapses and of the asymmetry of the network.
متن کاملMemory capacity of terminal attractor optical associative memory
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 m...
متن کامل