Topological Insulator Optoelectronic Synapses for High‐Accuracy Binary Image Recognition using Recurrent Neural Networks

Abstract

AbstractArtificial optoelectronic synapses have drawn tremendous attention in neuromorphic computing due to their exceptional properties of incorporating optical‐sensing and synaptic functions. However, the complex fabrication processes and device architectures greatly limit their applications. More importantly, artificial neural networks (ANNs) commonly implemented with optoelectronic synapses cannot take full advantage of the time‐dependent data of synaptic devices, resulting in defective accuracies. Here, facile two‐terminal optoelectronic synapses based on topological insulator Sb2Te3 films are fabricated, which exhibit significant photocurrent responses, owing to the efficient light‐matter interaction in bulk and the topological surface state of Sb2Te3. The performance of Sb2Te3 devices can be tuned both optically and electrically. Typical characteristics of synapses, such as paired‐pulse facilitation, short‐term memory, long‐term memory, and learning behavior, have been demonstrated. With the establishment of recurrent neural networks (RNNs) that are committed to processing temporal data, the as‐fabricated synapse devices are employed for binary image recognition of handwritten numbers “0” and “1”. The recognition accuracy of RNNs can reach as high as 100%, which is dramatically higher than those of ANNs. The effective employment of temporal data with RNNs ensured high recognition accuracy. These Sb2Te3 optoelectronic synapses with RNNs indicate the great potential for developing high‐performance brain‐inspired neuromorphic computing.