Abstract
We performed a comparative study on the Gaussian noise and memristance variation tolerance of three crossbar architectures, namely the complementary crossbar architecture, the twin crossbar architecture, and the single crossbar architecture, for neuromorphic image recognition and conducted an experiment to determine the performance of the single crossbar architecture for simple pattern recognition. Ten grayscale images with the size of 32 × 32 pixels were used for testing and comparing the recognition rates of the three architectures. The recognition rates of the three memristor crossbar architectures were compared to each other when the noise level of images was varied from −10 to 4 dB and the percentage of memristance variation was varied from 0% to 40%. The simulation results showed that the single crossbar architecture had the best Gaussian noise input and memristance variation tolerance in terms of recognition rate. At the signal-to-noise ratio of −10 dB, the single crossbar architecture produced a recognition rate of 91%, which was 2% and 87% higher than those of the twin crossbar architecture and the complementary crossbar architecture, respectively. When the memristance variation percentage reached 40%, the single crossbar architecture had a recognition rate as high as 67.8%, which was 1.8% and 9.8% higher than the recognition rates of the twin crossbar architecture and the complementary crossbar architecture, respectively. Finally, we carried out an experiment to determine the performance of the single crossbar architecture with a fabricated 3 × 3 memristor crossbar based on carbon fiber and aluminum film. The experiment proved successful implementation of pattern recognition with the single crossbar architecture.
Highlights
The memristor, the new fourth basic circuit element, was mathematically proposed by L
A comparative study was performed on the Gaussian noise and memristance variation tolerance of the complementary crossbar architecture, the twin crossbar architecture, and the single crossbar architecture
The three architectures were tested for pattern recognition under conditions of memristance variations
Summary
The memristor, the new fourth basic circuit element, was mathematically proposed by L. Memristor crossbars have opened opportunities to implement artificial neural networks on chips where the synaptic weights of network are stored in crossbar array [10,11,12,13] These potential applications, require huge computational tasks and training processes. Micromachines 2021, 12, 690 where memristor arrays were used for neuromorphic pattern recognition, including speech recognition and image recognition [14,15]. The complementary architecture, in which one memristor crossbar is the inversion of the other, is used for the application of speech recognition [14] It is based on a logical Exclusive-NOR (XNOR) operation, which measures the similarity of two binary arrays [14]. The twin crossbar architecture consumes less power than the complementary crossbar architecture for the application of image recognition. We performed an experiment on the single crossbar architecture with fabricated 3 × 3 memristor crossbar based on carbon fiber and aluminum film for storing and recognizing three simple patterns
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
