Memristor crossbar based unsupervised training

Abstract

Several big data applications are particularly focused on classification and clustering tasks. Robustness of such system depends on how well it can extract important features from the raw data. For big data processing we are interested for a generic feature extraction mechanism for different applications. Autoencoder is a popular unsupervised training algorithm for dimensionality reduction and feature extraction. In this work we have examined memristor crossbar based implementation of autoencoder which will consume very low power. We have designed on-chip training circuitry for the unsupervised training scheme.