One-Phototransistor-One-Memristor Array with High-Linearity Light-Tunable Weight for Optic Neuromorphic Computing

The recent advances in optic neuromorphic devices have led to a subsequent rise in use for construction of energy-efficient artificial-vision systems. The widespread use can be attributed to their ability to capture, store, and process visual information from the environment. The primary limitations of existing optic neuromorphic devices include nonlinear weight updates, cross-talk issues, and silicon process incompatibility. In this study, a highly linear, light-tunable, cross-talk-free, and silicon-compatible one-phototransistor-one-memristor (1PT1R) optic memristor is experimentally demonstrated for the implementation of an optic artificial neural network (OANN). For optic image recognition in the experiment, an OANN is constructed using a 16 x 3 1PT1R memristor array, and it is trained on an online platform. The model yields an accuracy of 99.3% after only ten training epochs. The 1PT1R memristor, which shows good performance, demonstrates its ability as an excellent hardware solution for highly efficient optic neuromorphic and edge computing.

Automated summary

The recent advances in optic neuromorphic devices have enabled the development of energy-efficient artificial-vision systems. These devices are widely used due to their ability to capture, store, and process visual information. However, existing optic neuromorphic devices have limitations such as nonlinear weight updates, cross-talk issues, and silicon process incompatibility. This study introduces a highly linear, light-tunable, cross-talk-free, and silicon-compatible optic memristor for the implementation of an optic artificial neural network (OANN). The experimental results show that the OANN achieves an accuracy of 99.3% after ten training epochs, demonstrating the effectiveness of the proposed optic memristor as a hardware solution for efficient optic neuromorphic and edge computing.