All-Fiber Synapse Utilizing Phase Change Materials for Information Recognition and Processing

Optical fiber has been widely used in telecommunication networks due to its inherent advantages of considerable bandwidth and ultrahigh-speed light transmission. However, it only serves as the transmission medium and cannot identify and process data directly in the fiber. One solution is to simulate neuromorphic functions directly in fibers. Here, Ge2Sb2Te5-assisted all-fiber synapses are proposed for information recognition and processing. The synaptic spike-timing-dependent plasticity, an important synaptic learning rule in Hebbian theory, can be mimicked by controlling the taper extension of the tapered fiber and integrating Ge2Sb2Te5 on its waist. The designed all-fiber synapse interacts efficiently with Ge2Sb2Te5 to alter light transmission, expressed as the synaptic weight. This synapse exhibits 10-level weight, 22% transmission contrast ratio, and 180 ns fast switching time for a single pulse. Additionally, the character recognition and arithmetic operation functions are demonstrated based on the proposed all-fiber synapses, inspiring a new paradigm for in-fiber processing.

Automated summary

In this study, Ge2Sb2Te5-assisted all-fiber synapses are proposed for information recognition and processing in optical fibers. By controlling the taper extension of the tapered fiber and integrating Ge2Sb2Te5 on its waist, the synaptic spike-timing-dependent plasticity can be mimicked. The all-fiber synapse interacts efficiently with Ge2Sb2Te5 to alter light transmission, resulting in 10-level weight, 22% transmission contrast ratio, and 180 ns fast switching time.