Performance of Pulse-Programmed memristive crossbar array with bimodally distributed stochastic synaptic weights

Identificador:  imarina:9454160

Handle: https://hdl.handle.net/20.500.11797/imarina9454160

Autores:  Dersch, N; Perez, E; Wenger, C; Roemer, C; Schwarz, M; Iniguez, B; Kloes, A

Resumen:
In this paper, we present a method of implementing memristive crossbar arrays with bimodally distributed weights. The bimodal distribution is a result of pulse-based programming. The memristive devices are used for implementing synaptic weights and can only have an ON (logical "1 '') or an OFF (logical "0 '') state. The state of the memristive device after programming is determined by the bimodal distribution. The highly efficient noisebased variability approach is used to simulate this stochasticity. The memristive crossbar array is used to classify the MNIST data set and comprises more than 15,000 weights. The interpretation of these weights is investigated. In addition, the influence of the stochasticity of the weights and the accuracy of the weights on the classification results is considered and various programming settings are examined.