Bidirectional associative memories
IEEE Transactions on Systems, Man and Cybernetics
The behavior of forgetting learning in bidirectional associative memory
Neural Computation
An Accurate Measure for Multilayer Perceptron Tolerance to Weight Deviations
Neural Processing Letters
Finite Precision Error Analysis of Neural Network Hardware Implementations
IEEE Transactions on Computers
Assessing the Noise Immunity and Generalization of Radial Basis Function Networks
Neural Processing Letters
Noise-Resistant Fitting for Spherical Harmonics
IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Computers
Stability and statistical properties of second-order bidirectional associative memory
IEEE Transactions on Neural Networks
Improving Leung's bidirectional learning rule for associative memories
IEEE Transactions on Neural Networks
Encoding strategy for maximum noise tolerance bidirectional associative memory
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
In neural networks, network faults can be exhibited in different forms, such as node fault and weight fault. One kind of weight faults is due to the hardware or software precision. This kind of weight faults can be modelled as multiplicative weight noise. This paper analyzes the capacity of a bidirectional associative memory (BAM) affected by multiplicative weight noise. Assuming that weights are corrupted by multiplicative noise, we study how many number of pattern pairs can be stored as fixed points. Since capacity is not meaningful without considering the error correction capability, we also present the capacity of a BAM with multiplicative noise when there are some errors in the input pattern. Simulation results have been carried out to confirm our derivations.