Area efficient low-sensitivity lumped madaline based on Continuous Valued Number System

The finite precision of inputs and weights in analog implementation of neural networks degrades the output response. The output response degradation is modeled by Noise-to-Signal-Ratio (NSR). Furthermore, neuron×NSR is an indicator of structure efficiency. In this paper, a new lumped Madaline architecture for networks with a large number of inputs and high input and weight variation is proposed. The information redundancy present in Continuous Valued Number System (CVNS) is exploited to improve the NSR. Moreover, the mathematical analysis of the NSR of Madalines based on previously developed structures and the proposed structure is conducted. The comparison shows that the proposed structure compares favorably to previously developed lumped architectures in terms of NSR and neuron×NSR.