Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses

TLDR

In an increasingly data‑rich world, the need for computing systems that can process and interpret big data is pressing, and brain‑inspired concepts show promise to address this. The study demonstrates unsupervised learning in a probabilistic neural network using metal‑oxide memristive devices as multi‑state synapses. The network processes unlabeled data and adapts to time‑varying clusters via reversible unsupervised learning enabled by the memristive synapses. Successful learning was demonstrated even with corrupted inputs and probabilistic neurons, indicating the approach’s robustness for big‑data processors.

Abstract

Abstract In an increasingly data-rich world the need for developing computing systems that cannot only process, but ideally also interpret big data is becoming continuously more pressing. Brain-inspired concepts have shown great promise towards addressing this need. Here we demonstrate unsupervised learning in a probabilistic neural network that utilizes metal-oxide memristive devices as multi-state synapses. Our approach can be exploited for processing unlabelled data and can adapt to time-varying clusters that underlie incoming data by supporting the capability of reversible unsupervised learning. The potential of this work is showcased through the demonstration of successful learning in the presence of corrupted input data and probabilistic neurons, thus paving the way towards robust big-data processors.